

Experienced quantitative professional specializing in credit risk and advanced analytics, with hands-on expertise in machine learning, statistical modelling, optimization, Python, SQL and Azure, and an M.Tech in Operations Research from IIT Bombay.
Simplifying Decision Trees | Masters Thesis
In Data Mining, especially while dealing with the data from social context, there is huge problem of overfitting which makes the decision trees complex and difficult to interpret. Observed that grouping similar values of variables into relatively homogenous subsets will significantly reduce the complexity of decision trees without much loss of accuracy resulting into highly interpretable easy to understand model as people lack trust in black boxes.
Recognising Human Actions using Sequential Deep Learning
Studied advanced deep learning algorithms like Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) can be used for the video analytics.