Machine Learning for Finance

Table of contents

1. Chapter 1 : Financial Data Understanding, EDA, and Feature Engineering
   1. The Course Overview 00:06:04
   2. Visualization, EDA, and Feature Engineering of Financial Data 00:06:40
   3. Features of the Stock Data 00:04:32
   4. Univariate and Bivariate Analysis of Data 00:14:29
   5. Deriving Moving Average and RSI Based Features 00:06:03
   6. Data cleaning and Outlier Detection 00:06:20
   7. Creating the Features and Independent Variable 00:06:37
   8. Prepare Data for Modeling 00:03:38
2. Chapter 2 : Predicting the FOREX Currencies by Building a Linear Model
   1. Linear Regression Intuition 00:05:41
   2. Understanding of FOREX Markets Data 00:04:14
   3. Pre-Process FOREX Currency Data for Model Input 00:10:48
   4. Building the Linear Regression Model 00:06:55
   5. R-Squared and Adjusted R-Squared as a Performance Metric 00:04:19
   6. The Testing Significance of Features by Using p-value and VIF 00:08:12
   7. Hyperparameter Tuning and Final Model Selection 00:08:26
3. Chapter 3 : Tree-Based Machine Learning Techniques for Stock Prediction
   1. Decision Trees Intuition 00:04:55
   2. Entropy and Information Gain Criterion for Tree Construction 00:07:06
   3. Building a Decision Tree-Based Model for Predicting Stock Prices 00:03:06
   4. Train Using Different Max Depth 00:04:13
   5. Random Forest Intuition 00:03:22
   6. Build a Random Forest Regressor for Predicting Stock Prices 00:03:54
   7. Boosting and XGBoost Based Regression Model for Stock Prediction 00:04:34
4. Chapter 4 : Artificial Neural Networks Basics and Intuition
   1. What a Neural Network Is 00:08:40
   2. Feed Forward in Neural Networks 00:04:32
   3. Gradient Descent in Neural Networks 00:05:42
   4. Back Propagation in Neural Networks 00:07:53
   5. Loss Function in Neural Networks 00:04:09
   6. Hyperparameters in Neural Networks 00:08:00
5. Chapter 5 : Stock Price Prediction by Using Artificial Neural Networks
   1. Prepare Data for Ingestion into the Neural Network 00:03:27
   2. Define the Neural Network Layers and Model 00:02:41
   3. Visualize Keras Model by using Pydot 00:02:52
   4. Train the Model Using Basic Parameters 00:02:12
   5. Analyze the Model Performance Using Loss and Accuracy Curves 00:01:34
   6. Hyperparameter Tuning of Neural Network 00:08:02
   7. Generating Predictions by Using the Trained Model 00:02:47
6. Chapter 6 : Modern Portfolio Theory and Techniques for Portfolio Management
   1. MPT and Stock Data Intuition 00:08:12
   2. Random Portfolio Generation and Portfolio Volatility 00:07:20
   3. Sharpe Ratio for Optimum Portfolio 00:03:45
   4. Portfolio Allocation Using Sharpe Ratio and Efficient Frontier 00:07:20
   5. Maximum Sharpe Ratio with SciPy Optimization 00:04:57
   6. Plotting and Visualizing Efficient Frontier 00:08:34
   7. Final Portfolio Allocation and Visualization 00:06:25
7. Chapter 7 : Predicting Fraud in Financial Transactions by Using ANN classification
   1. Softmax and Sigmoid Activation in Neural Networks 00:02:44
   2. Categorical Cross Entropy Loss for Classification 00:04:01
   3. Feature Engineering and Preprocess Data for Input into the Model 00:04:56
   4. Creating the Model and the Optimizer 00:02:24
   5. Training the Model 00:05:07
   6. Handling Class Imbalance 00:02:59
   7. Evaluating the Final Model and Predict Fraud Using the Model 00:05:27