19
Teradata Partners Conference ’14 Applying Topological Data Analysis to Complex Data Abhishek Gupta, Senior Engineer

Ayasdi & Teradata : Applying Topological Data Analysis to Complex Data

Embed Size (px)

DESCRIPTION

Ayasdi and Teradata launched our strategic partnership to enable mainstream business users and knowledge experts at large organizations to rapidly discover and act upon critical insights hidden in their massive and complex datasets.

Citation preview

Page 1: Ayasdi & Teradata : Applying Topological Data Analysis to Complex Data

Teradata Partners Conference ’14

Applying Topological Data Analysis to Complex Data

Abhishek Gupta, Senior Engineer

Page 2: Ayasdi & Teradata : Applying Topological Data Analysis to Complex Data

Company Confidential & Proprietary 2

Ayasdi named one of the Top 10 Most Innovative Companies in Big

Data for 2013

These big data companies are ones

to watch

The Structure Data Awards: Machine Learning / Artificial Intelligence

Top 100 Private Companies – Big Data/Analytics

Named by Mary Meeker as one of the most interesting

companies in the data/analytics space

Ayasdi makes the world’s complex data useful by extracting powerful insights automatically.

Page 3: Ayasdi & Teradata : Applying Topological Data Analysis to Complex Data

Company Confidential & Proprietary

The Promise of Big Data

3

Information Understanding Business Impact

Page 4: Ayasdi & Teradata : Applying Topological Data Analysis to Complex Data

Company Confidential & Proprietary

Why Do Current Approaches Fail?

4

Hypothesis

Today’s Approach to Analytics

Challenges: •  Incomplete and missing insights • Depends on humans to scale • Slow responses due to iteration

Page 5: Ayasdi & Teradata : Applying Topological Data Analysis to Complex Data

Company Confidential & Proprietary

A New Approach Is Required

5

Algorithms & Compute

Benefits: • Automated understanding • Comprehensive • Fast

OR

Page 6: Ayasdi & Teradata : Applying Topological Data Analysis to Complex Data

Company Confidential & Proprietary

Hypothesis

Comparison

6

Traditional Analytics Ayasdi Approach

Labor Intensive Automated

Analysts and Data Scientists Domain Experts Verifies Explains

Algorithms & Compute

or

Page 7: Ayasdi & Teradata : Applying Topological Data Analysis to Complex Data

Company Confidential & Proprietary 7

Statistics

Machine Learning

Geometry

Ayasdi’s topological framework incorporates, unifies and enhances other disciplines. Because of these properties

it has extraordinary reach and effectiveness.

Page 8: Ayasdi & Teradata : Applying Topological Data Analysis to Complex Data

Company Confidential & Proprietary

Ayasdi & Teradata Partnership

8

SQL Code DDL

Data pushed through analysis

Key Benefit: Making your ETL process simpler.

Page 9: Ayasdi & Teradata : Applying Topological Data Analysis to Complex Data

Company Confidential & Proprietary

Use Case: Anomaly Detection

ABOUT THE DATA

•  Data consists of die level test information for 1 wafer •  12,000+ dies with 100+ tests done for each of the die

•  Network was built using all the test columns

•  Test Result column with pass/fail flag used as metadata

GOAL OF THE ANALYSIS •  Identify different subgroups of dies based on similar test

information •  Find tests that uniquely identify failed die subgroups

9

Fortune 500 and S&P 500 company

$5B+ in revenue

Leader in flash memory

storage and software

Page 10: Ayasdi & Teradata : Applying Topological Data Analysis to Complex Data

Ayasdi CoreTM Demo

10

Page 11: Ayasdi & Teradata : Applying Topological Data Analysis to Complex Data

Company Confidential & Proprietary

Use Case: Anomaly Detection

11

High Low

Rows in Node

Page 12: Ayasdi & Teradata : Applying Topological Data Analysis to Complex Data

Company Confidential & Proprietary

Use Case: Anomaly Detection

12

High Low

Test Result=True

Key Takeaway: Tight concentration of wafers that pass their tests in the middle of the cluster

Page 13: Ayasdi & Teradata : Applying Topological Data Analysis to Complex Data

Company Confidential & Proprietary

Use Case: Anomaly Detection

13

High Low

Test Result=False

Key Takeaway: Two distinct regions of wafers failing their tests à Next action: investigate the “why”

Page 14: Ayasdi & Teradata : Applying Topological Data Analysis to Complex Data

Company Confidential & Proprietary

Use Case: Anomaly Detection

14

High Low

Test Result=False

Select first failure group to view underlying wafer properties

Page 15: Ayasdi & Teradata : Applying Topological Data Analysis to Complex Data

Company Confidential & Proprietary

Use Case: Anomaly Detection

15

KS scores for test 13 show correlations for specific failures

Page 16: Ayasdi & Teradata : Applying Topological Data Analysis to Complex Data

Company Confidential & Proprietary

Use Case: Anomaly Detection

16

High Low

Select second failure group to view underlying wafer properties

Page 17: Ayasdi & Teradata : Applying Topological Data Analysis to Complex Data

Company Confidential & Proprietary

Use Case: Anomaly Detection

17

KS scores for tests 8, 11, and 3 show correlations for specific failures

Page 18: Ayasdi & Teradata : Applying Topological Data Analysis to Complex Data

Company Confidential & Proprietary

Use Case: Anomaly Detection

18

SOLUTION •  Accelerated the analysis of wafer data and yield rates to identify

and resolve issues •  Identified additional systemic anomalies previously dismissed as

“random” •  Estimated to save hundred million dollars in the first year from a

reduction in scrap by reducing yield loss by 10%

CHALLENGE

•  Pinpoint wafer anomalies that result in scrap and lost revenue •  Previously required at least two days of analysis to identify even the

most systemic anomalies

Fortune 500 and S&P 500 company

$5B+ in revenue

Leader in flash memory

storage and software

Page 19: Ayasdi & Teradata : Applying Topological Data Analysis to Complex Data

Corporate Headquarters 4400 Bohannon Drive Suite #200 Menlo Park, CA 94025 ayasdi.com

19