Banking Crisis: This project focuses on building a predictive model to classify and forecast banking crises using economic indicators such as currency crises, inflation rates, and debt defaults. The aim is to develop a robust machine learning model to predict whether a banking crisis is likely to occur, enabling proactive risk management and decision-making. 

Systemic Bank Crisis: This data science task involves building a predictive model to forecast systemic crises, which are large-scale disruptions affecting financial systems. Using features like currency crises, inflation rates, and debt defaults, the project aims to create a reliable model for identifying early warning signals of systemic risks, helping stakeholders implement preventive measures effectively 

The Bank Churn Project focused on building a predictive model to identify customers likely to leave a bank. Using a dataset with features like account balance, transaction history, and credit score, machine learning techniques were employed to classify churn and non-churn cases. The model achieved high accuracy, providing valuable insights for proactive customer retention strategies. 

This Bank Loan Prediction Model aims to predict whether loan applications will be approved or not based on applicant details. Using features like income, education, credit history, and loan amount, the model employs machine learning techniques to make accurate predictions. The project is built to streamline loan approval processes and assist financial institutions in decision-making.

This Food Prices Dashboard in Power BI provides insights into food price trends across regions and timeframes. It highlights key metrics like minimum and maximum prices, food items, and states analyzed. Users can filter data by zone, state, year, month, and food name. Visuals include pie charts for price distribution, a bar chart for top food items, and a line chart for price trends, offering a concise tool for analyzing food price patterns. 

In this project, I built a machine learning model to predict food prices across various states in Nigeria, such as Lagos, Kano, Abuja, and Rivers, based on factors like the state, zone, food type, year, and month. The goal is to develop an accurate predictive model that can be deployed on the web for easy access and use.