Embed Size (px)
Citation preview
DISCLOSURE APPENDIX AT THE BACK OF THIS REPORT CONTAINS IMPORTANT DISCLOSURES, ANALYST CERTIFICATIONS, AND THE STATUS OF NON-US ANALYSTS. US Disclosure: Credit Suisse does and seeks to do business with companies covered in its research reports. As a result, investors should be aware that the Firm may have a conflict of interest that could affect the objectivity of this report. Investors should consider this report as only a single factor in making their investment decision.
CREDIT SUISSE SECURITIES RESEARCH & ANALYTICS BEYOND INFORMATION®
Client-Driven Solutions, Insights, and Access
16 October 2014
Asia Pacific/Australia
Equity Research
Quantitative Analysis
Quantitative Research QUANTITATIVE ANALYSIS
Alpha Ideas Series: An introduction to textual
analysis of conference calls
Given the significant increase in available computing power and data storage
capability over the past decade there has been an exponential increase in
research dedicated to textual analysis of financial releases and
management commentaries:
■ This has occurred because a shortcoming of pure quant investment
processes is that they typically lack direct contact with company
management compared to fundamental investment processes, where the
portfolio managers and analysts more regularly meet with management to
glean non-quantitative information from things such as body language, voice
modulation, tone, evasiveness, etc.
■ Accordingly, in an attempt to bridge this fundamental gap, quant investors
now use textual analysis techniques to analyse publically available
management communications to make a quantitative assessment of such
non-quantitative pieces of information.
This report therefore serves two primary purposes:
(1) For pure quant investors this report brings together all recent research and
general findings in the area of textual analysis of conference calls and
provides ideas about directions for further research on the topic; and
(2) It will help interested fundamental investors to understand how quant
investors are attempting to quantify qualitative information that they have
traditionally processed using their brain. The findings also provide rigor as
to why fundamental investors have had a competitive edge utilising these
non-quantitative pieces of information. Accordingly, this report therefore
also serves to crystallise what non-quantitative pieces of information
fundamental investors should be seeking to clearly discern, and who from,
in their direct management interactions.
The ideas in this report are entirely consistent with the recommendations from
Credit Suisse Head of Global Financial Strategies, Michael Mauboussin's recent
report Lessons from Freestyle Chess – Merging Fundamental and
Quantitative Analysis, i.e. it shows how quant investors are attempting to
merge their processes to be more fundamental in nature.
Research Analysts
Richard Hitchens
61 2 8205 4467
16 October 2014
Quantitative Research 2
An introduction to textual analysis of conference calls What is textual analysis?
For the purpose of financial analysis, textual analysis is simply the algorithmic processing
of a body of text to enable quantification of desired characteristics of the text, for example,
tone (how positive or negative is it) or readability (how easy or hard it is to read).
Why all the fuss?
Given the significant increase in available computing power and data storage capability
over the past decade there has been an exponential increase in research dedicated to
textual analysis of financial releases and management commentaries.
This has occurred because a shortcoming of pure quant investment processes is that they
typically lack direct contact with company management compared to fundamental
investment processes, where the portfolio managers and analysts more regularly meet
with management to glean non-quantitative information from things such as body
language, voice modulation, tone, evasiveness, etc.
Accordingly, in an attempt to bridge this fundamental gap, quant investors now use
textual analysis techniques to analyse publically available management
communications to make a quantitative assessment of such non-quantitative pieces
of information.
Purpose of this report
This report therefore serves two primary purposes:
(3) For pure quant investors this report brings together all recent research and general
findings in the area of textual analysis of conference calls and provides ideas about
directions for further research on the topic; and
(4) It will help interested fundamental investors to understand how quant investors are
attempting to quantify qualitative information that they have traditionally processed
using their brain. The findings also provide rigor as to why fundamental investors have
had a competitive edge utilising these non-quantitative pieces of information.
Accordingly, this report therefore also serves to crystallise what non-quantitative
pieces of information fundamental investors should be seeking to clearly discern, and
who from, in their direct management interactions.
The ideas in this report are entirely consistent with the recommendations from Credit
Suisse Head of Global Financial Strategies, Michael Mauboussin's recent report Lessons
from Freestyle Chess – Merging Fundamental and Quantitative Analysis, i.e. it shows
how quant investors are attempting to merge their processes to be more fundamental
in nature.
The remainder of this report is broken up into sections based on the various
characteristics of conference calls that have been quantitatively tested using textual
analysis. Each section explains the intuition behind the testing, the general
behavioural findings and any ideas for further research.
16 October 2014
Quantitative Research 3
Tone
Anecdotally, based on our discussions with fundamental investors, a primary non-
quantitative piece of information picked up on in their direct management dealings, that
can then influence their investment decision, is the tone of the language being used, i.e.
how positive or negative it is, and in particular how it has changed relative to their most
recent previous dealing.
Intuitively, the absolute level of, and change in, tone of management communications is
likely to be a reflection of current and near-term forward looking operational momentum,
which may tell you something in addition to earnings momentum. For example, two stocks
may experience the same percentage upgrade, but there may be a difference in tone of
communication potentially signifying a difference in conviction of the continuation of that
earnings momentum.
The general approach to tone textual analysis is to first create a tone dictionary by reviewing
a body of historical financial releases to determine the most commonly used financial terms
that have either positive or negative tone, e.g. upgrade, declining, growing, etc.
We performed such an analysis of our analyst reports earlier this year (for those
interested we ran through some of the difficulties and shortcomings that we faced in
performing the analysis in that report).
Once you have your tone dictionary you then write a simple algorithm to isolate all the
words in the text and count the number of positively and negatively toned words to
get an aggregate tone rating for the body of text.
One of the commonly cited shortcomings about tone textual analysis is that because you
create a dictionary from a body of past financial releases the dictionary: (1) is static to new
tone words that emerge over time; and (2) may have missed some words.
Given this it was with interest that we noted a recent proposal for a neat methodology to
create a dynamic tone dictionary1. The dictionary is created by calculating the
proportionate appearance of words in all recent news reports classified as being either
positive or negative based on the excess return on the day of announcement, i.e. the
market reaction to the news item.
The advantages of this approach are: (1) the dictionary is dynamic; (2) it is market derived;
(3) the tone of words that actually have no tone can change through time and this
approach will pick up on that where it is significant; and (4) the dictionary is larger given it
produces a tone score for each word.
In relation to point (3) above, an example is the word 'cancer'. If someone has 'cancer' it is
considered a negative, while if someone finds a cure for 'cancer' it is considered a positive,
so the tone of a word that has no tone could potentially change in its usage through time.
Application of tone textual analysis to conference calls
Tone analysis can be applied to all company releases, but particular emphasis has been
placed on result conference calls.
Conference calls first provide a formal Management Discussion (MD) and then a Question
and Answer section (Q&A), which enables sell-side and buy-side market participants to
ask questions about aspects of the result that are unclear and need clarification.
The Q&A is of particular interest because: (1) it is in theory presented in unscripted,
natural language, which enables analyses of the characteristics of the communicated text
compared to the reference of the MD; and (2) there may be new information in the addition
to that already provided in the result (both quantitative and qualitative).
16 October 2014
Quantitative Research 4
The primary finding2 in this area of textual analysis is that the tone in the Q&A of
conference calls has a link to short-term share price reaction, post-earnings-
announcement drift and abnormal trading volume that is not fully explained by concurrent
changes in standard earnings based metrics, whereas there appears to be little value in
tone analysis of the scripted MD.
Areas for further research
We believe the primary area of further research about tone and conference calls is in the
differences of tone between the various participants, where participants include amongst
others the Chief Executive Offer (CEO), Chief Financial Officer (CFO), Investor Relations
officer (IR), other corporate participants, sell-side analysts and buy-side investors.
Given the transcript identifies both the person asking and then the person answering the
question there is an opportunity to calculate tone at an individual level and then aggregate
thereafter for any other studies.
For example, how does the tone of questions differ to the tone of the answers? In
surveying our fundamental analyst team about their experiences of participation in
conference calls for later sections of this report, one analyst observed a trend towards
more bullish analysts being allowed to ask questions earlier in the conference call to set a
more positive questioning tone. He recalled a call where he was negative and got the first
question, and despite the result probably not being that negative, it appeared to set the
tone for the remainder of the call, which was on balance more negative than he thought it
may have been, had he not asked the first question.
Other dictionary based word themes
Having produced an algorithm to calculate tone (i.e. simply counting the number of words
in a text from a pre-defined dictionary and then calculating basic metrics) the researcher
can then test for any other word thematics simply by changing the dictionary.
To date there have been share price links found between proportions of words in financial
releases in the areas, amongst others of: praise, concreteness, activity, uncertainty
and deception. We discuss each of these briefly in turn.
Praise
Praise is somewhat similar to tone in nature because a company, who has operations that
are currently performing well and/or expected to do so in the future will be in a better
position to, and are more likely to, self-congratulate themselves. Hence, they would likely
be higher in use of words associated with praise.
Positive tone is about words such as upgrade, rising, increasing and growth, while praise
is about words such as accolade, appreciation, approval, celebration and recognition, so
we would therefore expect different signals to be produced, but they still may be fairly
highly correlated.
Similar to tone, given the same level of earnings surprise, two different companies may
have differing levels of praise reflective of their positivity towards their outlook, so praise
level may also provide alpha information in addition to quantifiable earnings metrics, which
is what has been found in practice3.
The Linguistic Inquiry and Word Count dictionary mentioned later in this report may have a
praise category ready for use, but if not you could easily use a thesaurus and an analysis
of usage within financial reports similar to producing a tone dictionary to produce a praise
dictionary.
16 October 2014
Quantitative Research 5
Concreteness
More recently there has been a push by regulators to encourage corporates to use more
concrete (as opposed to abstract) language in their financial releases to provide
investors with clearer communications.
By way of example of the difference between concrete and more abstract communication,
a company could guide:
"we will exceed 10% EPS growth in the next quarter", or
"we could exceed 10% EPS growth in the next quarter"
As you can see it is the words will and could that cause the difference between the two
statements being concrete and being more abstract.
To test whether concreteness affects investor behaviour there was a recent experiment4,
where participants were split into two groups and given the same word-for-word annual
financial release, but one group had all of the concrete words highlighted, while the other
group had all the abstract words highlighted.
Despite the words in totality being exactly the same, there were marked differences
between the two groups comfort in investing in the company, highlighting that
concreteness does affect investor behaviour.
As shown above the types of words that determine whether a passage of text is concrete
or abstract are somewhat unusual types of words.
Given this, we note that within the field of psychology there is a methodology known as
The Linguistic Category Model5, which classifies words as adjectives, state verbs, stat
action verbs, interpretative action verbs and descriptive action verbs to measure
concreteness.
In essence, it is a manual algorithm that enables a reader to determine how concrete or
abstract a body of text is by following the tagging rules set out in the model, whilst
manually reading the text.
The model was first published in 1988 at a time when computer power was weak and text
algorithms were fairly basic. Given significant developments since then, we have
determined that algorithms known as "part-of-speech tagging" algorithms will likely be
the most useful for automation of this concept.
Finally on concreteness, a recent alternate definition3, where it was defined as the
occurrence of words characterised by tangibility and materiality, including words amongst
others such as: payments, factory, estate, savings, finance and scientist, was used to find
a link between share prices and concreteness. Whilst these words are clearly quite
different to those highlighted above, it is nevertheless supportive of the behavioural
findings that concrete language is sought after by investors, and that further research in
the area of concreteness will likely be fruitful for quant investors.
Activity
Words associated with activity were also targeted in the same paper3. In describing their
activity indicator the authors commented:
"On the one hand, activity increases with the usage of words falling into the categories of
aggression, accomplishment, communication and motion. On the other hand, the z-scores
of categories representing cognitive terms, passivity and embellishment are deducted from
the activity indicator. To illustrate, words such as completion, launch, achieving or
strengthens will increase the value of activity, while shutdown, standstills, constrained
and puzzled will lead to its decrease."
16 October 2014
Quantitative Research 6
Similar to concreteness, the paper finds a positive link between share prices and activity.
Again these results are suggestive that further research in the area of activity will likely be
fruitful for quant investors
Uncertainty
Another category of words that anecdotally fundamental investors are on the lookout for in
management commentaries are words associated with risks or uncertainty.
While we haven't seen any results linking the level of management usage of words
associated with uncertainty in their answers in the Q&A of the call, we would expect that
high usage may be a red flag worth exploring.
That said in a recent an attempt6 to assess how rigorous and objective sell-side analyst
research is, there is a good dictionary of uncertainty words. The attempt found that analysts
significantly increase questions about uncertainty following a negative earnings surprise.
Interestingly, as an aside, in conjunction with this finding and a number of others, it was
concluded that sell-analyst research was far more rigorous and objective following a
negative earnings surprise than a positive earnings surprise.
There are a variety of structural reasons why this behavioural finding makes intuitive
sense. Accordingly, based on the finding, immediately after a company result any analysts
who were previously forecasting a result above the actual result may have slightly more
accurate forecasts than those analysts that had a prior forecast below the actual result.
This may potentially lead to a smarter consensus.
Deception
In the fields of psychology and linguistics there has been a lot of research dedicated to
detecting textual characteristics of deceptive language. Accordingly, approaches to
capture these text characteristics from financial releases, and in particular conference calls,
have been used to estimate probabilities of deceptive commentary for the purpose of
forecasting future shareholder returns.
On balance evidence7 from the fields of psychology and linguistics suggest deceptive
comments are more likely to be: (1) reflective of dissociation, i.e. less self-references; (2)
shorter; (3) more indirect; (4) more general; and (5) more evasive.
To make assessments about these characteristics researchers typically make use of a
psychosocial dictionary known as the Linguistic Inquiry and Word Count (LIWC) dictionary.
In a paper7 that used this dictionary, the authors utilised many of the different word
categories to detect the probability of deceptive commentary for both the CEO and CFO
for a subset of conference calls, which based on some screening criteria, were deemed to
have a reasonable probability of including deceptive commentaries based on known
subsequent events.
A variety of results were found highlighting that CEOs and CFOs appear to go about
deceptive commentary in different ways, but that CFOs are less able to conceal
deceptive commentary, such that there was an alpha link with assessing their
probability of deceptive commentary, whereas there wasn't for CEOs.
For fundamental investors this is a useful finding because it indicates that, when
having direct dealings with corporate management, efforts to think of questions that
target specific insights from corporate participants other than the CEO will likely be
rewarded with more informative answers.
16 October 2014
Quantitative Research 7
Readability
Another area of textual analysis that has been used extensively across a variety of
financial releases is readability. The intuition is that if a company has a good story to tell
then they will tell it clearly and succinctly, whereas if the story is less than desirable it will
be told less clearly and succinctly (which usually translates to larger words and longer
sentences).
We introduced our clients to readability in our report Readability – An introduction and
then applied some of the techniques to our own analyst reports.
Whilst we have not seen readability directly used in the analysis of conference calls, we
note that in the paper discussed in the previous section on deception it was found that
there was a positive association between word count and the probability of deception for
CFOs (but not CEOs), which is consistent with the intuition behind readability.
We believe that application of readability analysis to the MD and answers from the Q&A,
and in particular, if there is a significant difference between two, i.e. much less readable
answers, that this could be a potential red flag.
Informativeness
As mentioned previously tone has received criticism for being based on a fixed dictionary,
while readability has been criticised because it doesn’t take account of the content of the
words, rather just counts letters and words.
Accordingly, another aspect of conference calls, in addition to tone and readability, that
has recently received increased focus is informativeness, i.e. how much new information
is being provided in the answers in the Q&A of the conference call?
The Q&A enables market participants to ask questions about aspects of the result or
outlook that were not well explained in the financial release, and as such there may be
new information that comes to light in the answers. The new information may be of a
quantifiable nature, i.e. hard numbers, or alternatively unquantifiable soft information.
Supporting the view that new information does come to light is that past research8 has
shown that conference calls increase analysts' ability to forecast earnings accurately,
suggesting that these calls do increase the total information available about a firm.
Adding to the existing textual analysis literature9 was a recently introduced method of
calculating the informativeness of the answers from the Q&A of conference calls
compared to the MD. The approach used a complex cosine similarity test, but simplistically
the approach effectively stripped out duplicated words from both sections of the
conference call to get two sets of unique words and then correlated the two. If they are
highly correlated then informativeness is low and conversely.
The inference is that if the management is concerned about aspects of their result then
they will more likely attempt to re-iterate statements provided in the MD and as such will
provide lower informativeness and hence likely lower future share price returns.
The beauty of the approach is that it enables the assessment of the informativeness of
each of the individuals within the corporation that participate in the call. For example, the
paper shows that the CEO is typically less informative than other employee participants,
so the more time the CEO speaks on a conference call the less informative the call will be.
These findings are consistent with the findings in the deception section of this report.
For fundamental investors this is a useful finding because it indicates that, when
having direct dealings with corporate management, efforts to think of questions that
target specific insights from corporate participants other than the CEO will likely be
rewarded with more informative answers.
16 October 2014
Quantitative Research 8
Scriptedness
Opposite of informativeness is another area of conference call research that has popped
up recently, which is scriptedness.
Effectively scriptedness is attempting to identify how much the management stick to the
script of their MD when answering the questions in the Q&A of the conference call, which
is largely the opposite of informativeness.
Adding to the existing textual analysis literature10
was a recently introduced method of
calculating the scriptedness of the answers from the Q&A of quarterly conference calls
compared to the MD.
The intuition is that it is likely (supported by our own anecdotal evidence) that the MD is
scripted by IR in the weeks leading up to the result announcement and then vetted by the
CEO/Board for final approval.
It is then hypothesised that the IR sits down with management to focus on any likely
negative questioning opportunities from the result that may be targeted by the investment
community to ensure a consistent message and one that remains on track, i.e. effectively
pre-script some likely answers.
In theory, the greater the pre-scripting effort, the more negative aspects of the result
there are, which may potentially indicate a less positive outlook for the company than
simply explained by quantitative information alone.
The methodology drew on computational stylistics developed in the linguistics literature to help
identify the authors of documents with unknown or disputed authorship. In this case it was
used to determine how much of the Q&A was likely written by the author of the MD, i.e. the IR.
In essence the method correlates (using the same cosine similarity method as for
informativeness) the function words, i.e. those with primarily grammatical functions and
include articles (e.g., a, an, the), conjunctions (e.g., and, or, so), pronouns (e.g., I, me, we),
prepositions (e.g., of, on, in), and auxiliary verbs (e.g., is, do, can), between the scripted
MD and the answers of the Q&A.
It has been shown in the field of linguistics that these function words are the best stylistic
discriminators between two authors because they are unrelated to the topic discussed,
and that they reflect minor or even unconscious preferences of the author, whereas the
large words in a passage of text are fairly text specific, not author specific. For example, if
the one author wrote two texts about cars and bears, then the large words, acceleration,
pistons, aerodynamics, etc. for the cars text, and hibernation, claws, salmon, etc. for the
bears text, would be unrelated to the author.
Accordingly, if the frequency of these function words is highly correlated then the level of
scripting is high and conversely.
Similar to other dictionary based text classification exercises this measure of
scriptedness requires a dictionary of function words to isolate using the text algorithm.
It was found that there is a negative relation between scriptedness and future share price
returns.
In another recent paper about readability of annual reports11
, where the intention was to
compare how repetitive two separate sections of annual reports were, the authors used a
copy detection software program known as Ferret (code to use Ferret can be found at
http://freecode.com/projects/ferret).
Interestingly, Ferret measures the similarity (or scriptedness) of two documents by
dividing the number of identical three-word sequences found in both documents (i.e.,
“matching trigrams”), by the total number of unique three-word sequences found in both
documents. Similarity is thus bounded between zero and one, with one indicating perfectly
identical documents and zero indicating no matching trigrams between the two documents.
16 October 2014
Quantitative Research 9
As you can see this technique potentially has other broader applications, but in this
case for example, it could be used to determine the scriptedness of answers in the
Q&A of conference calls compared to the MD.
Analyst participation in conference calls and hence ability to observe scriptedness?
In thinking about companies scripting conference call answers, we thought that in the US
it would potentially be easier for companies to physically script answers and read them
out when asked the expected question because companies can be headquartered in any
of the states, so live presentation of the conference call would either be less well attended
or not occur at all and as such the phone call would be the only option.
In Australia, however, with Sydney as the primary financial hub most companies provide a
live presentation option in Sydney, so accordingly are less able to physically script, but
certainly would be able to pre-rehearse scripted answers.
Despite many companies in Australia offering a live presentation of their conference call,
we anecdotally have noted that some of our fundamental analysts prefer to dial into the
conference call from their office. Given this, and to understand the ability of companies to
read pre-scripted answers, we surveyed our analysts with the question:
What % of the time do you listen to a result conference call on the phone rather than
attend the live session?
The results of the survey are presented in Figure 1.
Figure 1: Survey responses
% Phone Comment
80% On a result day with multiple results, 90% of the time conference call. If there is only 1 result,
100% try to attend live session.
80% Probably about 80% or more.
70% Increasingly on the phone. Probably 70%
5% Almost never – if they have a live event, I almost always attend – say 95% of the time
66% 2/3rds on the phone
80% Generally always attend live if that is an option. But fewer companies doing live. I would say
20% live, 80% phone these days.
30% 70% live, 30% phone
90% 90%
90% 90%
90% 90% due to multiple companies reporting on same day….
10% 10% – if there’s a public forum I go wherever possible.
100% Covering 17 stocks and multiple on each day, 100% on phone. Ideally I would attend all large
cap briefings but not possible.
95% Has been 95%.
75% 75%. Small cap companies are less likely to hold live briefings. Also tend to run into
multiples coys reporting on 1 day and time constraints of attending live. I used to attend more
live doing large caps.
69% Average Source: Credit Suisse
As you can see around 70% of the time analysts dial into conference calls primarily due to:
(1) multiple results on one day; (2) relative ease of note taking; (3) difference of location
between residence and the live call option; or (4) lack of a live call option.
The commentaries also suggest that the rate of live participation has been trending down
and that this is likely to continue because: (1) in the current low economic environment
analysts cover more sectors and stocks than in the past, so are more likely to have
multiple results on a given day; and (2) anecdotally the cost of a live option is causing
some companies in the current low growth economic environment to drop their live option.
Given this it suggests that there is increasing chance that direct scripting becomes more
possible even in Australia. Anecdotal feedback from our analysts suggests that they have
not seen direct script reading, but that there has been some evidence of pre-rehearsed
scripted responses.
16 October 2014
Quantitative Research 10
Call participation
Another area of research that is starting to get some attention is call participation. In
particular, which analysts are asking questions on the conference call?
In this area there was a recent interesting result12
found concerning analyst interest,
where a positive return spread was found between stocks with increasing analyst interest,
i.e. companies where non-covering analysts ask questions on the conference call,
compared to those with waning analyst interest, i.e. companies where covering analysts
don't ask questions on the conference call.
Essentially the results are consistent with analysts maximising their incentives to deploy
their finite resources to the most interesting positive outlook stocks in their coverage
universe.
We see broader research opportunities in the area of call participation. As discussed
earlier in this report, one of our analysts had observed that analysts with more bullish
views tend to get to ask their questions first on conference calls.
Given this observation it suggests that conference calls Q&A are being managed by
some companies to present themselves in their best possible light.
If some companies are managing their conference calls then measures that quantify
the degree to which companies are managing calls will also likely provide fruitful
signals about the future prospects of companies.
To get a better understanding of to what extent companies manage conference calls
we have engaged with our fundamental research team.
In particular, we surveyed our fundamental research team with the question:
Do you believe you have ever missed out on asking a question on a company conference
call due to you having a negative view on the company?
Of the respondents, 25% of them believe that they have been overlooked for a question as
a result of having a negative view on the company, which provides support that
management of conference calls does occur and that there is valuable information in
capturing the extent of conference call participant management.
If negative view analysts are being overlooked in the Q&A section then this is consistent
with the directional intention of the analyst interest finding above, which may actually be
an unintended component of their finding.
Given this result we have researched leading global conference call operators and found
PGi (or Premiere Global Services, Inc. http://au.pgi.com/), which anecdotally is commonly
used in Australia, as a leading global conference call operator. In reviewing their publically
disclosed event service offering (http://au.pgi.com/services/event/), we have found that
one of the services is participant screening as shown in Figure 2.
16 October 2014
Quantitative Research 11
Figure 2: PGi event services
Source: PGi
This again suggests that conference call participation can be managed and potentially
managed for the purpose of providing the most positive coverage of the corporate group
possible.
Accordingly, for further research we suggest a couple of possible measures of conference
call Q&A management could be:
(1) Slope of the rating profile of the individuals who ask questions. For example
in IBES, we note that they rate stocks between 1 and 5, where 1 is most positive
and 5 is most negative. On the basis of this rating system and the hypothesis that
calls may be managed such that more bullish analysts get to ask questions first,
then a high positive slope would be expected (particularly, if all analysts get to ask
a question) if the call has been managed in this way.
(2) Average rating of the participants on the call compared to the average rating
of all possible participants. Given the best rated stocks in IBES get a 1 then the
larger the negative deviation away from the average or consensus rating, the more
positively-biased management of the call has likely occurred or alternatively the
greater the potential for negative view analysts to have been overlooked.
Next generation techniques
All of what has preceded has relied on the processing of communicated written word, i.e.
the text, whereas research also shows that there are other channels through which
meaning may be transmitted in a spoken setting including the use of both voice and body
by those involved in the communication. These additional channels encompass voice
inflection, speech volume, speech rate, speech errors, facial expressions, hand gestures,
posture, and movements. The next generation will therefore look to tap voice and video
analysis techniques.
As an example a recent study13
examined managerial tone of voice using a unique set of
conference call audio files. Using specialised layered voice analysis software, they
measured the positive and negative emotional states (voice inflection) of managers and
related these vocal cues to stock returns.
Given the results of our conference call participation survey from our analysts it suggests
that fundamental investors are likely capturing less body related communication
transmissions than the past due to lower attendance of live calls, but are still capturing
voice related communication transmissions by listening into the call on the phone.
16 October 2014
Quantitative Research 12
Conclusion
For pure quant investors, this report shows that there are many facets of conference
calls that can be analysed systematically using textual analysis to quantify valuable non-
quantitative information to capture alpha that has traditionally been the domain of
fundamental investors.
For fundamental investors, this report serves to crystallise what non-quantitative pieces
of information they should be seeking to clearly discern, and who from, in their direct
management interactions. It also highlights that, despite the increased potential for quants
to capture information from the communicated word of management commentaries, there
still remains a significant gap in capturing information from other channels through which
meaning may be transmitted in a spoken setting, including the use of both voice and body
by those involved in the communication. Accordingly, picking up on investment signals
from the use of voice and body, e.g. voice inflection, speech volume, speech rate, speech
errors, facial expressions, hand gestures, posture, and movements, will likely remain a key
competitive advantage for fundamental investors for the foreseeable future, so should be
taken advantage of with clear purpose.
Endnotes
1. The Tone of Financial News and the Perceptions of Stock and CDS Traders,
Michael Liebmann, University of Freiburg (Germany), Alexei G. Orlov, Radford
University, Dirk Neumann, University of Freiburg, March 21, 2014.
2. Earnings Conference Calls and Stock Returns: The Incremental Informativeness
of Textual Tone, Journal of Banking and Finance, Vol. 36, No. 4, pp. 992-1011, 2012,
S. McKay Price , James S. Doran , David R. Peterson and Barbara A. Bliss.
3. Predicting Stock Market Returns Based on the Content of Annual Report
Narrative: A New Anomaly, Tomasz Piotr Wisniewski, University of Leicester, Liafisu
Sina Yekini, Sheffield Hallam University, July 30, 2014.
4. Does Concrete Language in Disclosures Increase Willingness to Invest?, W.
Brooke Elliott, University of Illinois at Urbana-Champaign, Kristina M. Rennekamp,
University of Illinois at Urbana-Champaign - Department of Accountancy, Brian J.
White, University of Texas at Austin - Department of Accounting, April 28, 2014.
5. The Linguistic Category Model (LCM) (Measuring Language Abstraction), Linda H.
M. Coenen, Liselotte Hedebouw, and Gün R. Semin, Manual Version June 2006,
http://www.cratylus.org/resources/uploadedFiles/1151434261594-8567.pdf
6. Does Equity Analyst Research Lack Rigor and Objectivity? Evidence from
Conference Call Questions and Research Notes, Catherine Salzedo, Lancaster
University - Department of Accounting and Finance, Steven Young, Lancaster
University - Department of Accounting and Finance, Mahmoud El-Haj, Lancaster
University - School of Computing and Communications, May 5, 2014.
7. Detecting Deceptive Discussions in Conference Calls, Journal of Accounting
Research, Vol. 50, Issue 2, pp. 495-540, 2012 , Rock Center for Corporate
Governance at Stanford University Working Paper No. 83, David F. Larcker and
Anastasia A. Zakolyukina.
8. Do Conference Calls Affect Analysts' Forecasts?, Robert M. Bowen , Angela K.
Davis and Dawn A. Matsumoto, University of San Diego - School of Business ,
University of Oregon and University of Washington - Department of Accounting.
9. Say it Again Sam: The Idiosyncratic Information Content of Corporate
Conference Calls, Jim Cicon, New Jersey Institute of Technology, February 1, 2014.
16 October 2014
Quantitative Research 13
10. Scripted Earnings Conference Calls as a Signal of Future Firm Performance,
Joshua A. Lee, Washington University in Saint Louis - John M. Olin Business School,
April18, 2104
11. Say Again? Assessing Redundancy in 10-K Disclosures, Richard A. Cazier,
Texas Christian University, Ray J. Pfeiffer Jr., Texas Christian University - Neeley
School of Business, August 26, 2014
12. Analyst Interest as an Early Indicator of Firm Fundamental Changes and Stock
Returns, Michael J. Jung, New York University - Leonard N. Stern School of Business,
M.H. Franco Wong, INSEAD; University of Toronto - Rotman School of Management,
Frank Zhang, Yale School of Management, August 12, 2014
13. The power of voice: Managerial affective states and future firm performance, Mayew, W.J., Venkatachalam, M., Journal of Finance, February 2011
16 October 2014
Quantitative Research 14
Companies Mentioned (Price as of 15-Oct-2014)
Premiere Global (PGI.N, $11.49)
Disclosure Appendix
Important Global Disclosures
I, Richard Hitchens, certify that (1) the views expressed in this report accurately reflect my personal views about all of the subject companies and securities and (2) no part of my compensation was, is or will be directly or indirectly related to the specific recommendations or views expressed in this report.
The analyst(s) responsible for preparing this research report received Compensation that is based upon various factors including Credit Suisse's total revenues, a portion of which are generated by Credit Suisse's investment banking activities
As of December 10, 2012 Analysts’ stock rating are defined as follows:
Outperform (O) : The stock’s total return is expected to outperform the relevant benchmark*over the next 12 months.
Neutral (N) : The stock’s total return is expected to be in line with the relevant benchmark* over the next 12 months.
Underperform (U) : The stock’s total return is expected to underperform the relevant benchmark* over the next 12 months.
*Relevant benchmark by region: As of 10th December 2012, Japanese ratings are based on a stock’s total return relative to the analyst's coverage universe which consists of all companies covered by the analyst within the relevant sector, with Outperforms representing the most attractive, Neutrals the less attractive, and Underperforms the least attractive investment opportunities. As of 2nd October 2012, U.S. and Canadian as well as European ra tings are based on a stock’s total return relative to the analyst's coverage universe which consists of all companies covered by the analyst within the relevant sector, with Outperforms representing t he most attractive, Neutrals the less attractive, and Underperforms the least attractive investment opportunities. For Latin Ame rican and non-Japan Asia stocks, ratings are based on a stock’s total return relative to the average total return of the relevant country or regional benchmark; prior to 2nd October 2012 U.S. and Canadian ratings were based on (1) a stock’s absolute total return potential to its current share price and (2) the relative attractiveness of a stock’s total return potential within an analyst’s coverage universe. For Australian and New Zealand stocks, 12 -month rolling yield is incorporated in the absolute total return calculation and a 15% and a 7.5% threshold replace the 10-15% level in the Outperform and Underperform stock rating definitions, respectively. The 15% and 7.5% thresholds replace the +10-15% and -10-15% levels in the Neutral stock rating definition, respectively. Prior to 10th December 2012, Japanese ratings were based on a stock’s total return relative to the average total return of the relevant country or regional benchmark.
Restricted (R) : In certain circumstances, Credit Suisse policy and/or applicable law and regulations preclude certain types of communications, including an investment recommendation, during the course of Credit Suisse's engagement in an investment banking transaction and in certain other circumstances.
Volatility Indicator [V] : A stock is defined as volatile if the stock price has moved up or down by 20% or more in a month in at least 8 of the past 24 months or the analyst expects significant volatility going forward.
Analysts’ sector weightings are distinct from analysts’ stock ratings and are based on the analyst’s expectations for the fundamentals and/or valuation of the sector* relative to the group’s historic fundamentals and/or valuation:
Overweight : The analyst’s expectation for the sector’s fundamentals and/or valuation is favorable over the next 12 months.
Market Weight : The analyst’s expectation for the sector’s fundamentals and/or valuation is neutral over the next 12 months.
Underweight : The analyst’s expectation for the sector’s fundamentals and/or valuation is cautious over the next 12 months.
*An analyst’s coverage sector consists of all companies covered by the analyst within the relevant sector. An analyst may cover multiple sectors.
Credit Suisse's distribution of stock ratings (and banking clients) is:
Global Ratings Distribution
Rating Versus universe (%) Of which banking clients (%)
Outperform/Buy* 45% (55% banking clients)
Neutral/Hold* 39% (50% banking clients)
Underperform/Sell* 14% (43% banking clients)
Restricted 3%
*For purposes of the NYSE and NASD ratings distribution disclosure requirements, our stock ratings of Outperform, Neutral, and Underperform most closely correspond to Buy, Hold, and Sell, respectively; however, the meanings are not the same, as our stock ratings are determined on a relative basis. (Please refer to definitions above.) An investor's decision to buy or sell a security should be based on investment objectives, current holdin gs, and other individual factors.
Credit Suisse’s policy is to update research reports as it deems appropriate, based on developments with the subject company, the sector or the market that may have a material impact on the research views or opinions stated herein.
Credit Suisse's policy is only to publish investment research that is impartial, independent, clear, fair and not misleading. For more detail please refer to Credit Suisse's Policies for Managing Conflicts of Interest in connection with Investment Research: http://www.csfb.com/research and analytics/disclaimer/managing_conflicts_disclaimer.html
16 October 2014
Quantitative Research 15
Credit Suisse does not provide any tax advice. Any statement herein regarding any US federal tax is not intended or written to be used, and cannot be used, by any taxpayer for the purposes of avoiding any penalties.
Important Regional Disclosures
Singapore recipients should contact Credit Suisse AG, Singapore Branch for any matters arising from this research report.
Restrictions on certain Canadian securities are indicated by the following abbreviations: NVS--Non-Voting shares; RVS--Restricted Voting Shares; SVS--Subordinate Voting Shares.
Individuals receiving this report from a Canadian investment dealer that is not affiliated with Credit Suisse should be advised that this report may not contain regulatory disclosures the non-affiliated Canadian investment dealer would be required to make if this were its own report.
For Credit Suisse Securities (Canada), Inc.'s policies and procedures regarding the dissemination of equity research, please visit http://www.csfb.com/legal_terms/canada_research_policy.shtml.
As of the date of this report, Credit Suisse acts as a market maker or liquidity provider in the equities securities that are the subject of this report.
Principal is not guaranteed in the case of equities because equity prices are variable.
Commission is the commission rate or the amount agreed with a customer when setting up an account or at any time after that.
To the extent this is a report authored in whole or in part by a non-U.S. analyst and is made available in the U.S., the following are important disclosures regarding any non-U.S. analyst contributors: The non-U.S. research analysts listed below (if any) are not registered/qualified as research analysts with FINRA. The non-U.S. research analysts listed below may not be associated persons of CSSU and therefore may not be subject to the NASD Rule 2711 and NYSE Rule 472 restrictions on communications with a subject company, public appearances and trading securities held by a research analyst account.
Credit Suisse Equities (Australia) Limited ..................................................................................................................................... Richard Hitchens
For Credit Suisse disclosure information on other companies mentioned in this report, please visit the website at https://rave.credit-suisse.com/disclosures or call +1 (877) 291-2683.
16 October 2014
Quantitative Research 16
References in this report to Credit Suisse include all of the subsidiaries and affiliates of Credit Suisse operating under its investment banking division. For more information on our structure, please use the following link: https://www.credit-suisse.com/who_we_are/en/This report may contain material that is not directed to, or intended for distribution to or use by, any person or entity who is a citizen or resident of or located in any locality, state, country or other jurisdiction where such distribution, publication, availability or use would be contrary to law or regulation or which would subject Credit Suisse AG or its affiliates ("CS") to any registration or licensing requirement within such jurisdiction. All material presented in this report, unless specifically indicated otherwise, is under copyright to CS. None of the material, nor its content, nor any copy of it, may be altered in any way, transmitted to, copied or distributed to any other party, without the prior express written permission of CS. All trademarks, service marks and logos used in this report are trademarks or service marks or registered trademarks or service marks of CS or its affiliates. The information, tools and material presented in this report are provided to you for information purposes only and are not to be used or considered as an offer or the solicitation of an offer to sell or to buy or subscribe for securities or other financial instruments. CS may not have taken any steps to ensure that the securities referred to in this report are suitable for any particular investor. CS will not treat recipients of this report as its customers by virtue of their receiving this report. The investments and services contained or referred to in this report may not be suitable for you and it is recommended that you consult an independent investment advisor if you are in doubt about such investments or investment services. Nothing in this report constitutes investment, legal, accounting or tax advice, or a representation that any investment or strategy is suitable or appropriate to your individual circumstances, or otherwise constitutes a personal recommendation to you. CS does not advise on the tax consequences of investments and you are advised to contact an independent tax adviser. Please note in particular that the bases and levels of taxation may change. Information and opinions presented in this report have been obtained or derived from sources believed by CS to be reliable, but CS makes no representation as to their accuracy or completeness. CS accepts no liability for loss arising from the use of the material presented in this report, except that this exclusion of liability does not apply to the extent that such liability arises under specific statutes or regulations applicable to CS. This report is not to be relied upon in substitution for the exercise of independent judgment. CS may have issued, and may in the future issue, other communications that are inconsistent with, and reach different conclusions from, the information presented in this report. Those communications reflect the different assumptions, views and analytical methods of the analysts who prepared them and CS is under no obligation to ensure that such other communications are brought to the attention of any recipient of this report. Some investments referred to in this report will be offered solely by a single entity and in the case of some investments solely by CS, or an associate of CS or CS may be the only market maker in such investments. Past performance should not be taken as an indication or guarantee of future performance, and no representation or warranty, express or implied, is made regarding future performance. Information, opinions and estimates contained in this report reflect a judgment at its original date of publication by CS and are subject to change without notice. The price, value of and income from any of the securities or financial instruments mentioned in this report can fall as well as rise. The value of securities and financial instruments is subject to exchange rate fluctuation that may have a positive or adverse effect on the price or income of such securities or financial instruments. Investors in securities such as ADR's, the values of which are influenced by currency volatility, effectively assume this risk. Structured securities are complex instruments, typically involve a high degree of risk and are intended for sale only to sophisticated investors who are capable of understanding and assuming the risks involved. The market value of any structured security may be affected by changes in economic, financial and political factors (including, but not limited to, spot and forward interest and exchange rates), time to maturity, market conditions and volatility, and the credit quality of any issuer or reference issuer. Any investor interested in purchasing a structured product should conduct their own investigation and analysis of the product and consult with their own professional advisers as to the risks involved in making such a purchase. Some investments discussed in this report may have a high level of volatility. High volatility investments may experience sudden and large falls in their value causing losses when that investment is realised. Those losses may equal your original investment. Indeed, in the case of some investments the potential losses may exceed the amount of initial investment and, in such circumstances, you may be required to pay more money to support those losses. Income yields from investments may fluctuate and, in consequence, initial capital paid to make the investment may be used as part of that income yield. Some investments may not be readily realisable and it may be difficult to sell or realise those investments, similarly it may prove difficult for you to obtain reliable information about the value, or risks, to which such an investment is exposed. This report may provide the addresses of, or contain hyperlinks to, websites. Except to the extent to which the report refers to website material of CS, CS has not reviewed any such site and takes no responsibility for the content contained therein. Such address or hyperlink (including addresses or hyperlinks to CS's own website material) is provided solely for your convenience and information and the content of any such website does not in any way form part of this document. Accessing such website or following such link through this report or CS's website shall be at your own risk. This report is issued and distributed in Europe (except Switzerland) by Credit Suisse Securities (Europe) Limited, One Cabot Square, London E14 4QJ, England, which is authorised by the Prudential Regulation Authority and regulated by the Financial Conduct Authority and the Prudential Regulation Authority. This report is being distributed in Germany by Credit Suisse Securities (Europe) Limited Niederlassung Frankfurt am Main regulated by the Bundesanstalt fuer Finanzdienstleistungsaufsicht ("BaFin"). This report is being distributed in the United States and Canada by Credit Suisse Securities (USA) LLC; in Switzerland by Credit Suisse AG; in Brazil by Banco de Investimentos Credit Suisse (Brasil) S.A or its affiliates; in Mexico by Banco Credit Suisse (México), S.A. (transactions related to the securities mentioned in this report will only be effected in compliance with applicable regulation); in Japan by Credit Suisse Securities (Japan) Limited, Financial Instruments Firm, Director-General of Kanto Local Finance Bureau (Kinsho) No. 66, a member of Japan Securities Dealers Association, The Financial Futures Association of Japan, Japan Investment Advisers Association, Type II Financial Instruments Firms Association; elsewhere in Asia/ Pacific by whichever of the following is the appropriately authorised entity in the relevant jurisdiction: Credit Suisse (Hong Kong) Limited, Credit Suisse Equities (Australia) Limited, Credit Suisse Securities (Thailand) Limited, regulated by the Office of the Securities and Exchange Commission, Thailand, having registered address at 990 Abdulrahim Place, 27th Floor, Unit 2701, Rama IV Road, Silom, Bangrak, Bangkok 10500, Thailand, Tel. +66 2614 6000, Credit Suisse Securities (Malaysia) Sdn Bhd, Credit Suisse AG, Singapore Branch, Credit Suisse Securities (India) Private Limited (CIN no. U67120MH1996PTC104392) regulated by the Securities and Exchange Board of India (registration Nos. INB230970637; INF230970637; INB010970631; INF010970631), having registered address at 9th Floor, Ceejay House, Dr.A.B. Road, Worli, Mumbai - 18, India, T- +91-22 6777 3777, Credit Suisse Securities (Europe) Limited, Seoul Branch, Credit Suisse AG, Taipei Securities Branch, PT Credit Suisse Securities Indonesia, Credit Suisse Securities (Philippines ) Inc., and elsewhere in the world by the relevant authorised affiliate of the above. Research on Taiwanese securities produced by Credit Suisse AG, Taipei Securities Branch has been prepared by a registered Senior Business Person. Research provided to residents of Malaysia is authorised by the Head of Research for Credit Suisse Securities (Malaysia) Sdn Bhd, to whom they should direct any queries on +603 2723 2020. This report has been prepared and issued for distribution in Singapore to institutional investors, accredited investors and expert investors (each as defined under the Financial Advisers Regulations) only, and is also distributed by Credit Suisse AG, Singapore branch to overseas investors (as defined under the Financial Advisers Regulations). By virtue of your status as an institutional investor, accredited investor, expert investor or overseas investor, Credit Suisse AG, Singapore branch is exempted from complying with certain compliance requirements under the Financial Advisers Act, Chapter 110 of Singapore (the "FAA"), the Financial Advisers Regulations and the relevant Notices and Guidelines issued thereunder, in respect of any financial advisory service which Credit Suisse AG, Singapore branch may provide to you. This research may not conform to Canadian disclosure requirements. In jurisdictions where CS is not already registered or licensed to trade in securities, transactions will only be effected in accordance with applicable securities legislation, which will vary from jurisdiction to jurisdiction and may require that the trade be made in accordance with applicable exemptions from registration or licensing requirements. Non-U.S. customers wishing to effect a transaction should contact a CS entity in their local jurisdiction unless governing law permits otherwise. U.S. customers wishing to effect a transaction should do so only by contacting a representative at Credit Suisse Securities (USA) LLC in the U.S. Please note that this research was originally prepared and issued by CS for distribution to their market professional and institutional investor customers. Recipients who are not market professional or institutional investor customers of CS should seek the advice of their independent financial advisor prior to taking any investment decision based on this report or for any necessary explanation of its contents. This research may relate to investments or services of a person outside of the UK or to other matters which are not authorised by the Prudential Regulation Authority and regulated by the Financial Conduct Authority and the Prudential Regulation Authority or in respect of which the protections of the Prudential Regulation Authority and Financial Conduct Authority for private customers and/or the UK compensation scheme may not be available, and further details as to where this may be the case are available upon request in respect of this report. CS may provide various services to US municipal entities or obligated persons ("municipalities"), including suggesting individual transactions or trades and entering into such transactions. Any services CS provides to municipalities are not viewed as "advice" within the meaning of Section 975 of the Dodd-Frank Wall Street Reform and Consumer Protection Act. CS is providing any such services and related information solely on an arm's length basis and not as an advisor or fiduciary to the municipality. In connection with the provision of the any such services, there is no agreement, direct or indirect, between any municipality (including the officials, management, employees or agents thereof) and CS for CS to provide advice to the municipality. Municipalities should consult with their financial, accounting and legal advisors regarding any such services provided by CS. In addition, CS is not acting for direct or indirect compensation to solicit the municipality on behalf of an unaffiliated broker, dealer, municipal securities dealer, municipal advisor, or investment adviser for the purpose of obtaining or retaining an engagement by the municipality for or in connection with Municipal Financial Products, the issuance of municipal securities, or of an investment adviser to provide investment advisory services to or on behalf of the municipality. If this report is being distributed by a financial institution other than Credit Suisse AG, or its affiliates, that financial institution is solely responsible for distribution. Clients of that institution should contact that institution to effect a transaction in the securities mentioned in this report or require further information. This report does not constitute investment advice by Credit Suisse to the clients of the distributing financial institution, and neither Credit Suisse AG, its affiliates, and their respective officers, directors and employees accept any liability whatsoever for any direct or consequential loss arising from their use of this report or its content. Principal is not guaranteed. Commission is the commission rate or the amount agreed with a customer when setting up an account or at any time after that.
Copyright © 2014 CREDIT SUISSE AG and/or its affiliates. All rights reserved.
Investment principal on bonds can be eroded depending on sale price or market price. In addition, there are bonds on which investment principal can be eroded due to changes in redemption amounts. Care is required when investing in such instruments. When you purchase non-listed Japanese fixed income securities (Japanese government bonds, Japanese municipal bonds, Japanese government guaranteed bonds, Japanese corporate bonds) from CS as a seller, you will be requested to pay the purchase price only.
Quantitative Research 2014 10 16 - Alpha Ideas Series - An introduction to textual analysis of conference calls.doc
