Anomaly Detection in Transactions using Deep Learning added

Finacial Domain/Anomaly Detection in Transactions using Deep Learning/readme.md

@@ -0,0 +1,38 @@
+# Anomaly Detection in Transactions using Deep Learning
+
+## 🎯 Goal
+The main goal of this project is to develop models to detect anomalies in financial transactions using three different deep learning algorithms: Recurrent Neural Networks (RNN), Convolutional Neural Networks (CNN), and Multi-Layer Perceptrons (MLP). The aim is to identify fraudulent transactions effectively.
+
+## 🧵 Dataset
+The dataset used for this project is `transactions.csv`, which contains synthetic transaction data with features like transaction amount, transaction type, account age, transaction location, and a binary label indicating if the transaction is fraudulent.
+
+## 🧾 Description
+This project involves the implementation of three different deep learning algorithms for anomaly detection in transactions: RNN, CNN, and MLP. Each model is trained to identify patterns in the transaction data and detect anomalies.
+
+## 🧮 What I had done!
+1. Generated a synthetic dataset of transactions.
+2. Performed Exploratory Data Analysis (EDA) to understand the data distribution and characteristics.
+3. Implemented three different models: RNN, CNN, and MLP.
+4. Trained and evaluated each model.
+5. Compared the models based on their accuracy scores.
+
+## 🚀 Models Implemented
+- **Multi-Layer Perceptron (MLP):** A basic neural network architecture used for classification tasks.
+- **Recurrent Neural Network (RNN):** An LSTM-based RNN model used for sequential data analysis.
+- **Convolutional Neural Network (CNN):** A 1D CNN model used for pattern recognition in sequential data.
+
+## 📚 Libraries Needed
+- pandas
+- numpy
+- seaborn
+- matplotlib
+- scikit-learn
+- tensorflow
+
+## 📊 Exploratory Data Analysis Results
+- Basic dataset information and statistics.
+- Distribution of transaction amounts, transaction types, account ages, and transaction locations.
+- Correlation matrix to identify relationships between features.
+- Visualization of fraudulent vs non-fraudulent transactions.
+
+