Back To Projects

Approaches to fraud detection on credit card transactions using artificial intelligence methods

Aryaman R.

In this paper, we study the problem of detecting fraudulent credit card transactions. We select the most relevant features using a heuristic approach, and fit three different model classes to a simulated dataset: Logistic Regression, Random Forests and Gradient Boosting Machines. We find that hyperparameter tuning has a big impact on the precision and recall of our classifiers. We also find that of the three classes, Gradient Boosting Machines were the best-performing model class, achieving 83% precision and 64% recall on unseen data.

In this paper, we study the problem of detecting fraudulent credit card transactions. We select the most relevant features using a heuristic approach, and fit three different model classes to a simulated dataset: Logistic Regression, Random Forests and Gradient Boosting Machines. We find that hyperparameter tuning has a big impact on the precision and recall of our classifiers. We also find that of the three classes, Gradient Boosting Machines were the best-performing model class, achieving 83% precision and 64% recall on unseen data.

Explore More!

Aryaman R.
Yuan Lee
EECS MEng from MIT

Related Projects

Predicting Shoe Prices Using Machine Learning Algorithms
This paper investigates the use of machine learning algorithms, particularly Support Vector Regression, to accurately predict shoe prices based on factors like material, color, brand, type, gender, and size, using a dataset of 5000 entries.
Akshar S.
Mentored by John Basbagill
Predicting Repeat Purchases in E-Commerce
The underlying problem here is identifying more efficient upselling strategies for retailer companies. These findings may potentially help a retail company determine the likelihood of a customer purchasing another item based on their first purchase, and then decide how to upsell based on that information.
Ayrton S.
Mentored by Bryce Johnson
workspace_premium
Applications of AI in Microfinance
I hope to explore how to use AI in the field of microfinance to help reduce income inequality. Microfinance has greatly helped decrease rural poverty rates in Bangladesh. The leader of this effort won the Nobel Peace Prize for his work. These micro-loans give opportunity to those who are not otherwise able to obtain financing for their entrepreneurial ideas. This can be applied in the U.S. too, in places where the population cannot otherwise obtain loans to start small businesses and climb their way out of poverty. It can be very difficult to start from rock bottom in the US, especially for those without access to resources. If people could obtain small loans and start small businesses, they could work their way out of poverty. The microloans have to be viable for banks as well. The problem I’d like to explore is whether AI/ML can be used to determine how to deploy microloans efficiently to address income inequality in the U.S.
Alex M.
Mentored by Odysseas Drosis
Inspirit AI

About Inspirit AI

Home Team Impact

Programs

Live Online Learn More Apply Now

Join Our Mailing List

Stay up to date with all things Inspirit AI!

Subscribe

© 2022 Inspirit AI. All Rights Reserved.

Terms and conditions | Refund policy | Privacy policy

Research Paper