Machine learning Python project

profilepallavisai
ProjectGuidelines.docx

Final Report:

To be limited to 10 pages (excluding computer printout and appendices). Your final report should discuss the model formulation and solution, highlighting the major contribution made by you through the project work, and difficulties encountered, deviation from the preliminary objectives, and significant conclusions.……

Project:

Implementation:

Credit card frauds detection approaches can be classified in two main families: supervised and unsupervised ones. In this project supervised techniques are used as they are more effective in detecting illegal transactions, although they require a large initial training set. In this, past transactions are labeled as legal or illegal, for instance, based on expert judgement or customer’s claims; the algorithms then learn over these data, to create a model that is applied to new instances appearing in the system.

The idea is to invest the data, check for data unbalancing, visualize the features and understand the relationship between different features and implement different supervised techniques like

Random forest Classifier,

SVM,

Neural network

K neighbors classifier,

logistic regression,

Linear discriminant analysis,

and compare the results.

Reference:

https://www.kaggle.com/mlg-ulb/creditcardfraud