Predicting purchase amount in Black Friday dataset. (MAE = 2195)

In this repo I'll use different types of datasets to explore and implement various Exploratory Data Analysis (EDA) approaches.

Data manipulation and assessment using Pandas

Cleaning and preparing the data of black friday sales for model training. Techniques involve are EDA and Feature Engineering.

Our aim was to find the relationship between number of purchases on Black Friday sales and variables such as occupation, marital status, age groups, gender, city category and number of years lived in a city. Another objective was to establish a market basket of items from product category A, B and C.

This project predicts sales amounts for various products during the annual Black Friday sales event. Leveraging machine learning techniques and historical sales data, I uncover patterns and insights to inform retailers' marketing strategies and inventory management decisions.

In this model we have tried to analyse sales of ABC limited, its basically a part of hackathon that our peers tried to compete in. In this project we have tried our best to get the lowest RMSE as possible and have implemented the XGBoost model. Rest of it is explained in the ReadMe file or code.