End-to-end project to predict the mental health status of Instagram users from their posts and images. Built Un-supervised LDA and Semi-supervised Topic Models using text features.
Built content based recommendation and also product based search recommendation system using ALS algorithm on Big Data
Found Similarity between documents using Jaccard Similarity and including Parts Of Speech(POS) Tags of the words in the model to better find the synchronous relationship between documents. Implemented Word embedding to understand the word clusters.
Finding the binary sentiment of the tweets(satisfied or not) and basics of text processing.
Analyzed web analytics data of 500+ customers with 700+ variables to improve the conversion rate of visitors to customers. Presented XGBoost model with suggestions to improve it's performance.