Video link to Presentation video

Main files to run in order: datathon.ipynb and then Classification Model.ipynb

Install pandas for data manipulation

pip install pandas

Install numpy for numerical computing

pip install numpy

Install scikit-learn for machine learning models and tools

pip install scikit-learn

Install lightgbm for LightGBM models

pip install lightgbm

Install matplotlib for plotting

pip install matplotlib

Install seaborn for statistical data visualization (optional, useful for plotting)

pip install seaborn

In the scr folder, please download currencyexchange.csv, rates.csv, and spending_predictions_months_11_to_14.csv.

In the same directory, we moved the folder data from the unziped folder given.

Diagram of the required files.

C:.
├───datathon.ipynb
├───Classification Model.ipynb
├───currencyexchange.csv
├───rates.csv
├───spending_predictions_months_11_to_14.csv
├───data
│   ├───account_dim_20250325.csv
│   ├───fraud_claim_case_20250325.csv
│   ├───fraud_claim_tran_20250325.csv
│   ├───rams_batch_cur_20250325.csv
│   ├───statement_fact_20250325.csv
│   ├───syf_id_20250325.csv
│   ├───transaction_fact_20250325.csv
│   └───wrld_stor_tran_fact_20250325.csv

We have other files that store output from our jupyter notebook, but are not needed to run it.