GayathriMadala/Detection-of-Fraud-in-Credit-Card-Transactions-using-Machine-Learning-Algorithms

Stars
1
Language
HTML
Created about 4 years ago
Updated about 4 years ago

GayathriMadala/Detection-of-Fraud-in-Credit-Card-Transactions-using-Machine-Learning-Algorithms

GayathriMadala

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

An application to detect and predict Credit Card fraudulent users by training the model using Data Mining algorithms like Predictive Modeling, Decision Trees, and Logistic Regression

SYNTHETIC-DATA-GENERATION-USING-GAN-AND-VAE

This paper focuses on Implemention of Deep Convolutional-Generative Adversarial Network and Variational Autoencoder for MNIST dataset consisting of 60000 records and for ANIME dataset of 80000 records and analyze the performance of both the models on these datasets

GNITS

This app “GNITS” consists of all the information regarding my college that can be accessed by anyone on downloading this app. It contains information regarding the different departments in the college, syllabus copies of various department, location of the college will be shown in the map and information regarding various Bus facilities provided by college etc.

Chat-Application

A chat application in JAVA with multi-threading ability to establish multiple user sessions for exchange of information and files

Analysis_on_Diabetes_data

In this project of "Performance Analysis of Supervised Machine Learning Techniques", various supervised algorithms namely Logistic Regression, KNearestNeighbors, Support Vector Machine, Decision Tree Classifier and Random Forest Classifier are applied on to real-time Diabetes dataset. This dataset has missing values and they are removed by applying both the mean imputation and median imputation techniques. This dataset is then normalized using Standard Scaler and MinMax Scaler. The cleaned and normalized data is further treated with the all 5 specified algorithms and their confusion matrices, accuracy scores, precision values and recall values are generated. These values are compared by generating corresponding bar graphs and the best algorithm, best imputation techniques are determined.

Jupyter Notebook

Gossip-Protocol

Implementation of Gossip protocol and push sum using Erlang to determine it's usefulness and how the algorithm scales with the size of the network.