As part of my final year undergrad project, being a team leader - I strategized and developed a 3-month long project using Machine Learning.

What is the Project About?

Depersonalize is a privacy-preserving network security project that aims at preserving the privacy of an individual using an Anonymization Method called K-Anonymity.

For our project, we experimented with this method using SelectK-Best to find the important attributes and pass these attributes to the K-anonymity algorithm to anonymize the dataset in a way that the complete dataset as a whole is anonymized, and thus the identifying data is removed. As a benchmark, we used a Big Basket dataset to demonstrate the implementation.

Technologies used

We used Python as the base language to implement the model. Here, we also used some Python libraries which provide base-level items because Python code is concise and readable even to new developers, which is beneficial to the machine. As Machine learning requires continuous data processing and Python libraries allow you to access, process, and transform your data. 

For the client and server side, we used HTML and CSS on the front end (for UI), and PHP on the backend (to render data and send it to Python script).

To generate and test the output, we used the Big Basket dataset as a benchmark dataset.

The implementation and Output

We implemented the entire code using the above-mentioned technologies after rigorous research, iterations, and testing.

The result was perfectly anonymized data that made sure no personally - identifying data is left over in the dataset. 

You can find the entire documentation here, the team presentation here, and the code implementation here.

Looking to hire a Product Consultant/Associate Product Manager? DM Me here :)