Machine learning model for Credit Card fraud detection

Spam detection in SMS messages with BERT model and Machine Learning algorithms

The aim to decrease the maintenance cost of generators used in wind energy production machinery. This is achieved by building various classification models, accounting for class imbalance, and tuning on a user defined cost metric (function of true positives, false positives and false negatives predicted) & productionising the model using pipelines.

Predict the enzyme class of a given FASTA sequence using deep learning methods including CNNs, LSTM, BiLSTM, GRU, and attention models along with a host of other ML methods.

System to tell apart the transaction was from the real user who owns the credit card or the transaction was from the stolen credit card.

Electricity Fraud Detection in Smart Grids

Prediction of basic soil nutrients (phosphorus, potassium, boron, calcium, magnesium and manganese) using reflectance from Hyperspectral Satellite Images (HSI).

An implementation of SMOTE

Credit Card fraud detection

A compilation of codes for SMA, DC, ADS

Repository for "Data Mining - Advanced Topics and Applications" projects exam.

A model that recommends University based on details of an applicant.

使用比赛方提供的脱敏数据，进行客户信贷流失预测。

Predicting the ability of a borrower to pay back the loan through Traditional Machine Learning Models and comparing to Ensembling Methods

Obstructive Sleep Apnea classification with help of numerical data set which having the physical body characteristics with the help of machine learing

RCSMOTE: Range-Controlled Synthetic Minority Over-sampling Technique for handling the class imbalance problem

Gear detection using OpenCv and Machine Learning

This project is a part of the research on PolyCystic Ovary Syndrome Diagnosis using patient history datasets through statistical feature selection and multiple machine learning strategies. The aim of this project was to identify the best possible features that strongly classifies PCOS in patients of different age and conditions.

This project develops an activity recognition model for a mobile fitness app using statistical analysis and machine learning. By processing smartphone sensor data, it extracts features to train models that accurately recognize user activities.