This repository features code for a fraud detection model achieving 100% accuracy in identifying fraudulent credit card transactions. Utilizing transaction data from Jan 2019 to Dec 2020, the model employs RandomForestClassifier, assessing features like credit card numbers, transaction amounts, and merchant information.

CNN model to classify garbage

Objective: Address the classification problem behind predicting credit risk

Artificial intelligence (AI, ML, DL) performance metrics implemented in Python

I'll use various techniques to train and evaluate a model based on loan risk. I will use a dataset of historical lending activity from a peer-to-peer lending services company to build a model that can identify the creditworthiness of borrowers.

Create a Logistic Regression model to predict the credit risk of customers to a lending company. Use historical data and train the model before making predictions of test data. Lastly write an analysis report on the models created.

Intrusion Detection System for MQTT Enabled IoT.

"TensorFlow Image Classification Project" This project demonstrates image classification using TensorFlow. The CIFAR-10 dataset, consisting of 60,000 32x32 color images across 10 classes, is explored and analyzed. Key components include data loading, dataset characteristics, and a machine learning model built using the functional API.

Conducted data analysis, statistical analysis, and data visualization on an Indian crime dataset. Applied various machine learning algorithms to gain insights from the data. Utilized Time-Series models for prediction and forecasting based on the crime data analysis.

3 modelos de classificação para analisar churn de um empresa de telecom e ao final responder a pergunta: Qual modelo teve o melhor desempenho?

The main purpose of our proposed method is used to predict the quality of water by using Machine Learning algorithm.

Objective: The department wants to build a model that will help them identify the potential customers who have a higher probability of purchasing the loan. This will increase the success ratio while at the same time reducing the cost of the campaign.

Trained a classifier by using labeled data and oversampling and undersampling techniques to predict if a borrower will default on a loan. The model is intended to be used as a reference tool to help investors make informed decisions about lending to potential borrowers based on their ability to repay. The purpose is to lower risk & maximize profit.

CNN to classify ultrasounds of cancerous and non cancerous cells

Understanding emotions from audio files using neural networks and multiple datasets.

Decision trees breast cancer dataset

In this project, I use 3 machine learning models (CART, Random Forest and ANN) to predict the claim frequency for a travel insurance firm. I also evaluate which of the three models is most suitable for our dataset.

Trained and evaluated two supervised machine learning models using original and resampled data to identify 'healthy loan' and 'high risk loan' applicants from financial disclosures.

NU Bootcamp Module 20

Supervised machine learning to train and evaluate models based on loan risk.