Learn about SCIKIT library and how to import it along with other libraries and data. Learn to create important indicators for the algorithm.
Learn about Hyper-parameters and Cross-validation for data pre-processing. Learn to create datasets, standardization and how to handle missing data. Learn to train and test your data.
Learn Regression in detail. Learn about errors and residuals in a regression model and how to predict them. Understand the Cost Function and Gradient Descent algorithm to minimize the cost function. Finally, learn about Multivariate Linear Regression and code w.r.t to linear regression.
Learn the concept of Prediction error and how to identify these errors in any Machine Learning algorithm. Learn about underfitting and overfitting the data and ways to get a good fit. Understand the concept of Regularization using lambda parameter.
Learn how to modify the predictions made by the regression to account for market conditions. Learn how to get actual market high and low predictions from raw predictions.
Learn the concept of classification and how to map input into a discrete category. Learn four types of classifier algorithms, which are K-Nearest Neighbor, Random Forest, Artificial Neural Network, and Naïve Bayes Classification. Learn various indicators such as RSI, SMA, Correlation co-efficient, Parabolic SAR and Average directional index.
Learn the concept of Binary Classification to predict the market direction. Learn the mathematical functions like Sigmoid and hyperbolic tangent to construct a binary classifier. Learn how to implement binary classification in financial market to predict market movement.
Understand the concept of Multiclass classification and how it is different from binary classification. Learn to classify datasets into more than one class using ‘One vs All’ algorithm. Learn how to categorize the data based on numeric encoding of categories followed by an explanation on ‘one hot encoding’. Learn the probability function and performance measures in ML and working of ‘Softmax’ function.
Learn the concept of Hyperplane, Support Vector, and Margin. Learn to how to choose the best hyperplane by maximizing the margin and the mathematics behind it. Learn about classification of non-linear data using kernel and understand different parameters such as C & Gamma and their effects on SVM algorithm.
Learn to build your own trading strategy based on the concepts learned earlier. Learn to properly import libraries, data and create necessary indicators. Learn to compare the strategy’s performance with market data. Learn to implement/modify the given strategy.