Since the outbreak of covid-19, companies have faced challenges in developing accurate demand forecasting models. In this project I explored different time-series forecasting models such as, ARIMA, LSTMs, GANs, Bayesian LSTMs, and Attention networks, in the forecasting of non-statonary demand data.
Used Technologies: Python 3.7, Tensorflow, pandas, PyTorch, scikit-learn, numpy
• Built a full-stack machine learning web application that classifies Amazon product reviews using natural language processing. The product helps customers clarify product selection based on keywords discussed in product reviews.
Used Technologies: Python 3.7, Flask, Heroku, LDA, NLTK