21/08/2023
Fuzzy Matching Company Names - S&P Global Market Intelligence, 2021
Built a string matching engine that deduplicates 40,000+ company names with the different abbreviations of legal structures, omissions and typographical errors in the names utilizing Natural Language Processing (NLP) with TF-IDF vectorizer.
Global Energy Trend with Fossil Fuel Price Prediction - S&P Global Market Intelligence, 2020
Built an interactive web interface using Python Dash and Plotly to provide insights into global energy trends and fossil fuel price predictions applying Seasonal ARIMA, STL Decomposition, Exponential Smoothing and Prophet time series models.
Energy Market Sentiment Analysis with NLP and LSTM - S&P Global Market Intelligence, 2020
Applied Long Short-Term Memory (LSTM) based Recurrent Neural Network (RNN) with NLP principles to predict how the sentiments behind energy-related news headlines impact the performance of the index value in the Oil and Gas industry.
Prediction of Capital and Operating Costs of Power Plants - S&P Global Market Intelligence, 2019
Applied multivariate regression to predict forward capital expenditures as well as operating expenses of power plants located in US by different fuel types and technology types leveraged.
Mapping Gas Power Plants to a Gas Hub in U.S. - S&P Global Market Intelligence, 2019
Created a Python application that maps US gas power plants to a gas hub district using K-Means clustering algorithm with Vincenty distance function to find a set of clusters such that every power plant of a hub is within 12 miles of every other power plant in the hub.
