ºÝºÝߣ

ºÝºÝߣShare a Scribd company logo

Building similarentityrecognizerv1

•Download as PPTX, PDF•
•
A
arthi v

The document discusses techniques for building similar entity recognizers to detect potentially fraudulent insurance claims and cross-selling opportunities. It describes challenges in entity matching, supervised and unsupervised learning approaches, and the use of semantic techniques. It also addresses handling large datasets through distributed computing and continuous learning.

1 of 17
Download to read offline
Building Similar Entity Recognizers By Arthi Venkataraman 1 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
Agenda Similar Entity Detection Scenarios Challenges, Techniques and Algorithms Semantic applicability Big Data Challenges and Solution Sample Results 2 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
Scenario 1 - Fraud Detection in Insurance Claims Are P1 , P2 and P3 same? Is there FRAUD P1 P2 Tom Harold Tom H makes claim makes claim on P3 on Policy 2 Policy 1 T Harold makes a claim on Policy 3 3 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
Scenario 2 – Cross Sell Potential Detection in Insurance Does Tom Harold hold a policy in any other system. What are the policies he holds. Is there a potential for cross sell. Tom Harold holds Policy 1 in System 1 He is high net-worth customer 4 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
Example features for different people Person 1 Person 2 Person 3 • First Name – • First Name – • First Name – Tom Tom Tom • Middle Name - • Middle Name - • Last Name - • Last Name - Harry Harold Harold • Last Name - • Date of Birth – • Date of Birth – Harold 20/10/1988 20/10/1987 • Date of Birth – • Address - • Address - 20/10/1987 1, Mahatma 1, MG • Address - Gandhi Road, Bangalore 1, Mahatma Rd, Bangalore - – 56 Gandhi 560056 Rd, Bangalore - 560056 Questions : • Is Person 1 same as Person2 ? • Is Person 2 same as Person3 ? • Is Person 1 same as Person3 ? 5 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
Similar Entity Detection Challenges Quick manual inspection of Person 1 and Person 2 feature data to conclude that Person 1 is same as Person 2 Not so trivial for a machine Weightages must be arrived at for different features Code is needed for identifying if values of a feature for person 1 and person 2 are similar or different A similar string comparison is not sufficient - Is MG Road same as Mahatma Gandhi Rd Actual data will have some spelling mistakes, missing data and wrongly entered data. For e.g. 20/10/1987 could be entered as 20/10/1988 Or the field itself could be empty Hence need other techniques like machine learning and semantic techniques 6 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
Similar Entity Detection Methodology Given two entities how can we say that two entities are same • Identify relevant features Step 1 • Extract values for the features Step 2 • Create a model which can classify the Step 3 two entities as same or different • Use the model to classify future Step 4 customer pairs 7 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
Supervised Learning model Labeled pre-identified customer pairs data as inputs Values for different features for each of the customer pairs Each customer pair is tagged as Same, Probably Same, Different A supervised algorithm is chosen - ( Actual algorithm based on data characteristics ) The tagged data is fed as input Output is the model Model will classify a new customer pair into one of the identified categories Model accuracy can be calculated using the Precision, Recall, Accuracy and F-Scores 8 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
Supervised Learning model example • Live example of how to classify a given set of customer records using Supervised Learning 9 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
Un-Supervised Learning model In many cases there is no pre-labeled data In this case we would need to choose an Un- supervised learning model The model will automatically detect patterns in the data and cluster the data points into different clusters Any newly added customer pair would be placed in the right cluster 10 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
Un-Supervised Learning model example • Live example of how to classify a given set of customer records using Un-Supervised Learning 11 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
Continuous Learning In many cases there will be some small set of labeled data and very large set of un- labeled data An initial model will be created using the small labeled data set As more labeled data is available the model will evolve due to continuous learning and become more better at the classification 12 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
Semantic Techniques applicability Semantic similarity scoring for features • Feature - List of Games played • Person 1 plays – Racquet Sports • Person 2 plays – Lawn Tennis • Using semantic comparison we can see that there is a high similarity between person 1 and person 2 on the List of Games played feature Extraction of features from different data sources • Similar features named differently Associating customers in different data sources as same or different • Flexibly and easy addition of new relationships Ease of adding additional data sources 13 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
Large Data handling challenges Entity similarity is a pair wise operation If there are n entities then there n*(n-1) number of comparisons to be done Also within each comparison for every feature pair has to be compared Highly time consuming operations 14 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
Large Data handling ideas Use of Apache Mahout • Split the comparison into m different machines • Each machine now handles - n/m customer • Nearly an m time speed-up Batch time Incremental comparisons and addition of new tagging customer pairs • Reduce run time response to find similar entities 15 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
Sample Metrics from our experiments • Discussion on the sample metrics from our experiments • Learning from same – Which algorithm and method was more apt under different circumstances 16 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
Thank You 17 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL

More Related Content

Building similarentityrecognizerv1

  • 1. Building Similar Entity Recognizers By Arthi Venkataraman 1 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
  • 2. Agenda Similar Entity Detection Scenarios Challenges, Techniques and Algorithms Semantic applicability Big Data Challenges and Solution Sample Results 2 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
  • 3. Scenario 1 - Fraud Detection in Insurance Claims Are P1 , P2 and P3 same? Is there FRAUD P1 P2 Tom Harold Tom H makes claim makes claim on P3 on Policy 2 Policy 1 T Harold makes a claim on Policy 3 3 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
  • 4. Scenario 2 – Cross Sell Potential Detection in Insurance Does Tom Harold hold a policy in any other system. What are the policies he holds. Is there a potential for cross sell. Tom Harold holds Policy 1 in System 1 He is high net-worth customer 4 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
  • 5. Example features for different people Person 1 Person 2 Person 3 • First Name – • First Name – • First Name – Tom Tom Tom • Middle Name - • Middle Name - • Last Name - • Last Name - Harry Harold Harold • Last Name - • Date of Birth – • Date of Birth – Harold 20/10/1988 20/10/1987 • Date of Birth – • Address - • Address - 20/10/1987 1, Mahatma 1, MG • Address - Gandhi Road, Bangalore 1, Mahatma Rd, Bangalore - – 56 Gandhi 560056 Rd, Bangalore - 560056 Questions : • Is Person 1 same as Person2 ? • Is Person 2 same as Person3 ? • Is Person 1 same as Person3 ? 5 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
  • 6. Similar Entity Detection Challenges Quick manual inspection of Person 1 and Person 2 feature data to conclude that Person 1 is same as Person 2 Not so trivial for a machine Weightages must be arrived at for different features Code is needed for identifying if values of a feature for person 1 and person 2 are similar or different A similar string comparison is not sufficient - Is MG Road same as Mahatma Gandhi Rd Actual data will have some spelling mistakes, missing data and wrongly entered data. For e.g. 20/10/1987 could be entered as 20/10/1988 Or the field itself could be empty Hence need other techniques like machine learning and semantic techniques 6 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
  • 7. Similar Entity Detection Methodology Given two entities how can we say that two entities are same • Identify relevant features Step 1 • Extract values for the features Step 2 • Create a model which can classify the Step 3 two entities as same or different • Use the model to classify future Step 4 customer pairs 7 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
  • 8. Supervised Learning model Labeled pre-identified customer pairs data as inputs Values for different features for each of the customer pairs Each customer pair is tagged as Same, Probably Same, Different A supervised algorithm is chosen - ( Actual algorithm based on data characteristics ) The tagged data is fed as input Output is the model Model will classify a new customer pair into one of the identified categories Model accuracy can be calculated using the Precision, Recall, Accuracy and F-Scores 8 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
  • 9. Supervised Learning model example • Live example of how to classify a given set of customer records using Supervised Learning 9 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
  • 10. Un-Supervised Learning model In many cases there is no pre-labeled data In this case we would need to choose an Un- supervised learning model The model will automatically detect patterns in the data and cluster the data points into different clusters Any newly added customer pair would be placed in the right cluster 10 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
  • 11. Un-Supervised Learning model example • Live example of how to classify a given set of customer records using Un-Supervised Learning 11 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
  • 12. Continuous Learning In many cases there will be some small set of labeled data and very large set of un- labeled data An initial model will be created using the small labeled data set As more labeled data is available the model will evolve due to continuous learning and become more better at the classification 12 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
  • 13. Semantic Techniques applicability Semantic similarity scoring for features • Feature - List of Games played • Person 1 plays – Racquet Sports • Person 2 plays – Lawn Tennis • Using semantic comparison we can see that there is a high similarity between person 1 and person 2 on the List of Games played feature Extraction of features from different data sources • Similar features named differently Associating customers in different data sources as same or different • Flexibly and easy addition of new relationships Ease of adding additional data sources 13 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
  • 14. Large Data handling challenges Entity similarity is a pair wise operation If there are n entities then there n*(n-1) number of comparisons to be done Also within each comparison for every feature pair has to be compared Highly time consuming operations 14 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
  • 15. Large Data handling ideas Use of Apache Mahout • Split the comparison into m different machines • Each machine now handles - n/m customer • Nearly an m time speed-up Batch time Incremental comparisons and addition of new tagging customer pairs • Reduce run time response to find similar entities 15 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
  • 16. Sample Metrics from our experiments • Discussion on the sample metrics from our experiments • Learning from same – Which algorithm and method was more apt under different circumstances 16 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL
  • 17. Thank You 17 © 2012 WIPRO LTD | WWW.WIPRO.COM | INTERNAL