Comparison of a Logistic Regression, Support Vector Machine and Neural Network model for sentiment analysis using Bag-of-words and Word Embeddings for feature extraction

This is one project is one I really enjoyed. It is based off of my “Introduction to Machine Learning” class. The goal was to be able to predict whether a review was good or bad using data from three domains:,, and This data was obtained from the paper by D Kotzias, M Denil, N De Freitas, P Smyth (2005) which was presented at the KDD ’15: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data . Here, I have used 2400 data samples of one-sentence reviews and their corresponding labels whether positive or negative (positive = 1, negative = 0) which will be split into training and testing sets. More details on this project can be found below:

Application of Artificial Neural Networks in Predicting Critical Rates for Vertical Wells in Oil Rim Reservoirs

Critical coning rate determination as a measure of preventing coning in oil fields with underlying aquifers and overlying gas caps are a fundamental aspect of production planning in field development plans. This has always been carried out using existing correlations having large error margins. This study is aimed at developing a more accurate prediction model based on artificial neural network. The resulting paper was presented at the SPE Nigeria Annual International Conference and Exhibition, July 2017 and published in a top Petroleum Engineering Journal. 

A Comprehensive Classification Model for Predicting Wildfires with Uncertainty

Wildfires are a serious environmental problem today, heightened by the menace of global warming and climate change. Using a comprehensive dataset, 11 classification models were used to predict whether or not there is an occurrence of wildfire using the three feature variables: Normalized Difference Vegetation Index (NDVI), Land Surface Temperature (LST) and the Thermal Anomalies (referred to as the BURNED_AREA in the dataset). The aim of this work is to compare the performance of different Machine learning models (with careful hyperparameter selection) for wildfire prediction.