Portfolio

Natural Language Processing

Detect Non-negative Airline Tweets: BERT for Sentiment Analysis

The release of Google's BERT is described as the beginning of a new era in NLP. In this notebook I'll use the HuggingFace's transformers library to fine-tune pretrained BERT model for a classification task. Then I will compare BERT's performance with a baseline model, in which I use a TF-IDF vectorizer and a Naive Bayes classifier. The transformers library helps us quickly and efficiently fine-tune the state-of-the-art BERT model and yield an accuracy rate 10% higher than the baseline model.

Detect Food Trends from Facebook Posts: Co-occurence Matrix, Lift and PPMI

First I build co-occurence matrices of ingredients from Facebook posts from 2011 to 2015. Then, to identify interesting and rare ingredient combinations that occur more than by chance, I calculate Lift and PPMI metrics. Lastly, I plot time-series data of identified trends to validate my findings. Interesting food trends have emerged from this analysis.

Data Science

Kaggle Competition: Predict Ames House Price using Lasso, Ridge, XGBoost and LightGBM

I performed comprehensive EDA to understand important variables, handled missing values, outliers, performed feature engineering, and ensembled machine learning models to predict house prices. My best model had Mean Absolute Error (MAE) of 12293.919, ranking 95/15502, approximately top 0.6% in the Kaggle leaderboard.

Kaggle Competition : Instacart Market Basket Analysis

Instacart is an American technology company that operates as a same-day grocery delivery and pick up service in the U.S. and Canada. Customers shop for groceries through the Instacart mobile app or Instacart.com from various retailer partners. The order is shopped and delivered by an Instacart personal shopper.We can utilize this anonymized transactional data of customer orders over time to predict which previously purchased products will be in a user’s next order.

Recommendation Systems

News-Articles-Recommendation

Objective of the project is to build a hybrid-filtering personalized news articles recommendation system which can suggest articles from popular news service providers based on reading history of twitter users who share similar interests (Collaborative filtering) and content similarity of the article and user’s tweets (Content-based filtering). This system can be very helpful to Online News Providers to target right news articles to right users.

Netflix Movie Recommendation System

Netflix is all about connecting people to the movies they love,to help customers find those movies, they developed world-class movie recommendation system: CinematchSM. Its job is to predict whether someone will enjoy a movie based on how much they liked or disliked other movies.Netflix use those predictions to make personal movie recommendations based on each customer’s unique tastes.We aim to Predict the rating that a user would give to a movie that he has not yet rated.

Deep Learning

Music-Generation-Using-Deep-Learning

This case-study focuses on generating music automatically using Recurrent Neural Network(RNN). We do not necessarily have to be a music expert in order to generate music. Even a non expert can generate a decent quality music using RNN. Our input to the model is a sequence of musical events/notes. Our output will be new sequence of musical events/notes. In this case-study we have limited our self to single instrument music as this is our first cut model.

Real-Time-Facial-Expression-Recognition

Computer animated agents and robots bring new dimension in human computer interaction which makes it vital as how computers can affect our social life in day-to-day activities. Face to face communication is a real-time process operating at a time scale in the order of milliseconds. The level of uncertainty at this time scale is considerable, making it necessary for humans and machines to rely on sensory rich perceptual primitives rather than slow symbolic inference processes. In this project I am presenting the real time facial expression recognition of seven most basic human expressions: ANGER, DISGUST, FEAR, HAPPY, NEUTRAL, SAD, SURPRISE.