Back

Speaker "Suman Kumar" Details Back

 

Topic

Application of Ensemble Machine Learning and Big data to help Financial Institutions detect payment fraud & prevent crime losses and reduce false positives.

Abstract

Financial institutions are under tremendous pressure due to rapid changes in fraud landscape. FIs are majorly facing dual challenges: financial damage and loss of customers trust & shareholders value. The rapid advancement in technologies has enabled fraudster with easy access to information which is being leveraged for committing crime. In the recent past, data scientists have been using several predictive models and machine learning algorithms like Logistic Regression, decision tree, Neural Network, Support Vector machines, etc. to predict fraud. However advance feature engineering has not been emphasized enough to build a predictive algorithms. Too many features can create complexities while predicting fraud, create over fitting problem and also hamper model accuracy. We would be applying a novel approach for feature engineering to select right set of optimized features and build robust & consistent algorithms. To prevent fraud & crime losses and improve customer experience, we have proposed an ensemble approach of Generalized Linear Model and Gradient Boosting Models. Gradient Boosting Model has been built for predicting errors produced by GLM and then later a standalone GBM model has been built. Error predictive score was ensemble with Stochastic GBM to avoid overfitting, reduce variance and improve accuracy.

Profile

Suman is the Chief Analytics Officer for ZAFIN has a strong background in predictive analytics and machine learning techniques across domains such as Finance, Retail and Industrial. He has successfully built and developed high performance analytics team from scratch for global organizations. He is an expert in building technology enabled analytics solution and finding innovative patterns and insights to solve complex business problems. He has developed and launched Relationship analytics product (miInsights) to solve bottom line business problems for retail banking and offer relationship optimization & enhancement, product & price optimization, offering right bundle of product & services through a single platform. miInsights product is powered by high computing data processing engine to create thousands of features and score millions of customers' behavior using high end machine & deep learning algorithms with massive parallel processing engine in few minutes & couple of hours.