Name: Judith Boluwatito TOBOGBE
Type: User
Bio: Passionate Data Science professional with expertise in Deep Learning, NLP, and AI, committed to making impactful contributions to these fields.
Location: Benin
Judith Boluwatito TOBOGBE's Projects
This project analyzes fake and real news articles using NLP techniques and an SVM classifier. By performing sentiment analysis, word cloud, and bar chart visualizations, we identified common themes and linguistic patterns in both types of news. The resulting model achieved high accuracy in predicting whether an article is fake or real.
This project develops a machine learning model to predict hourly stock levels for Gala Groceries. The Python module simplifies training and evaluation, incorporating the Random Forest Regressor algorithm and performance metrics like RMSE and MAE. By using the module, Gala Groceries can optimize inventory management and make data-driven decisions.
This project analyzes SpaceX's approach to rocket launches, predicts success of future Falcon 9 launches using API data, and aims to build classification models to predict first stage landings. Insights will inform our commercial space travel industry approach.
Analyze and visualize loan data using Python. Explore loan trends, borrower behavior, and factors influencing outcomes. Interactive visualizations and predictive models for informed lending decisions. Enhance financial data-driven insights.
Explore insights into customer churn and price sensitivity for PowerCo, a leading gas and electricity utility, through Python-driven data analysis. This repository includes tasks covering business understanding, exploratory data analysis, feature engineering, and predictive modeling.
This repository contains a real estate dataset dashboard built to illustrate insightful trends and patterns within the housing market. The dashboard features comprehensive data visualizations crafted from the provided real estate dataset, offering a compelling narrative about key metrics and market dynamics.
The main objective of the project is to predict which customers out of the 1000 new customers in the New Customer are likely to buy bikes.
This GitHub project analyzes European soccer data from July 2008 to May 2016, providing insights and answers to statistical questions related to players and the game. The data is sourced from Kaggle and is available for open-source use.