1

Maximo. Watson Analytics!

Cindy Biando – Thomas Schwartz March 2016

2 2 2

Please note

IBM’s statements regarding its plans, directions, and intent are subject to change or withdrawal without notice at IBM’s sole discretion.

Information regarding potential future products is intended to outline our general product direction and it should not be relied on in making a purchasing decision.

The information mentioned regarding potential future products is not a commitment, promise, or legal obligation to deliver any material, code or functionality. Information about potential future products may not be incorporated into any contract. The development, release, and timing of any future features or functionality described for our products remains at our sole discretion.

Performance is based on measurements and projections using standard IBM benchmarks in a controlled environment. The actual throughput or performance that any user will experience will vary depending upon many factors, including considerations such as the amount of multiprogramming in the user’s job stream, the I/O configuration, the storage configuration, and the workload processed. Therefore, no assurance can be given that an individual user will achieve results similar to those stated here.

IBM ANALYTICS PLATFORM

Discovery &

Exploration

Prescriptive

Analytics Streaming

Analytics

Business Intelligence & Predictive Analytics

Content

Analytics

Information Integration & Governance

Data

Management

Content

Management

Hadoop

System

Data

Warehousing

The IBM analytics platform

Breadth & depth

of analytics

Data integration

& governance Hybrid & fluid

architecture

Open & unified

platform

Create a new data

foundation for the

business

Prepare data

for analytics

Predict the future

for the business

Align data management

strategy with customer

expectations

Delight customers

by understanding

them better

Derive business value

from unstructured

content

Watson Analytics

4

Watson Analytics Value Proposition

1. Advanced Analytic tool available now!

2. Competitive Differentiator thru

(1) Data Refinement (2) Data Exploration

(3) Predictive Analysis and (4) Infographic Dashboards

3. Works with data from multiple products including: Maximo, Industry Solutions, RTI and more!

4. Customer usage accelerated thru – Cloud Based Platform – Complex, individual models not required – Subscription Pricing – Ease of Use. Statistician Skill Set not required.

5

Watson Prediction uses historical data analysis to identify Relationship between Asset Downtime and Sensor values

Global Manufacturing example

Maximo/RTI and Watson Analytics: Asset Downtime Use Case

Integration between Watson and Maximo/RTI:

• Export data from Maximo/RTI to csv file. Import to Watson Analytics.

• Relationship between asset and sensors established

Net benefits: • Unexpected influencers of downtime identified in minimal amount of time • Corrective actions prioritizing sensor value (Alerts, PMs, Material Sourcing) can be

taken to reduce downtime and maintenance costs and improve production schedules

Highest downtime areas darkened

Predictors of Downtime Analyzed..Critical Sensor Value Identified

Additional Influencers identified : Asset Age and Sensor Dates

Demo

7

Next Steps

1. Build out library of demo .csv files

8

ASSET

SENSOR

WORKORDER

FAILUREREPORTING

65K records

ASSETSTATUS

ASSET

Trends of Downtime, Failures Problem, Cause, Remedy

???

2. Investigate development of product offering

Backup

9

Data: Quality

10

Grades data based on completeness, balanced values, and outliers -Red/Yellow/Green coding focuses user on non-performing data

Identifies fields with > 25% missing values Identified fields with data imbalances

Data: Refinement

11

Provides tools to review and refine each attribute’s quality

Individual grades

Higher Grades -> Improved Exploration and Analytic Capability

Exploration

12

Type in what you would like to explore

Or have Watson suggest explorations to you

13

Exploration

Build understanding of data

Save Explorations as ‘Collections’ for future use in Data Assemblies

Highest Downtime Countries in dark colors

Total Downtime by Country

Number of Assets by City

Shenzen has highest downtime. Detroit has 2nd highest downtime with small number of assets)

14

Predict

Evaluation of data for pattern recognition….Influencers

15

Predict

Deeper understanding of data influencers

Assemble

16

InfoGraphics dashboard!

- Display of Explore and Predict Collections + Unique Charts

Assemble

17

Representations of data via unique, user configurable options

Backup

18

19 19 19

Please note

IBM’s statements regarding its plans, directions, and intent are subject to change or withdrawal without notice at IBM’s sole discretion.

Information regarding potential future products is intended to outline our general product direction and it should not be relied on in making a purchasing decision.

The information mentioned regarding potential future products is not a commitment, promise, or legal obligation to deliver any material, code or functionality. Information about potential future products may not be incorporated into any contract. The development, release, and timing of any future features or functionality described for our products remains at our sole discretion.

Performance is based on measurements and projections using standard IBM benchmarks in a controlled environment. The actual throughput or performance that any user will experience will vary depending upon many factors, including considerations such as the amount of multiprogramming in the user’s job stream, the I/O configuration, the storage configuration, and the workload processed. Therefore, no assurance can be given that an individual user will achieve results similar to those stated here.