Inspiration

After watching the documentary Inside Job, which explores the impact of insider trading, we were inspired to take action. When we learned there was a financial track at this hackathon, we saw this opportunity to address a real-world problem by making it easier to detect and prevent this serious crime.

What it does

Uses Meta Data of Chat, calls , emails , batch swipes, and file accesses to detect if any suspicious activity revolving insider trading is happening.

Main.py upload the data , 6 files CSV extracted from the servers. Analyse uses the trained model to predict if there is any suspicious activity. See results of suspicious activities based on the ANN.

How we built it

Wrote scripts to generate artificial data to train the model and then a different set of data to test the model.

Merged and cleaned all CSV files to make sure that the data is consistent and are there no empty fields. Wrote the front end using Tkinter.

Challenges we ran into

Getting the test and training data for the ANN, and making the ANN.

Accomplishments that we're proud of

Getting the ANN to provide accurate results, and building the ANN.

What we learned

We learned more about machine learning and how we an ANN can be implemented.

What's next for Insider Trading Tracker

Better user interface and better trading data.

Built With

• csv
• python
• vscode