1. Learn
    2. /
  2. Courses
    3. /
  3. Machine Learning for Finance in Python
  • 1

    Preparing data and a linear model

    Free

    In this chapter, we will learn how machine learning can be used in finance. We will also explore some stock data, and prepare it for machine learning algorithms. Finally, we will fit our first machine learning model -- a linear model, in order to predict future price changes of stocks.

  • 2

    Machine learning tree methods

    Learn how to use tree-based machine learning models to predict future values of a stock's price, as well as how to use forest-based machine learning methods for regression and feature selection.

  • 3

    Neural networks and KNN

    We will learn how to normalize and scale data for use in KNN and neural network methods. Then we will learn how to use KNN and neural network regression to predict the future values of a stock's price (or any other regression problem).

  • 4

    Machine learning with modern portfolio theory

    In this chapter, you'll learn how to use modern portfolio theory (MPT) and the Sharpe ratio to plot and find optimal stock portfolios. You'll also use machine learning to predict the best portfolios. Finally, you'll evaluate performance of the ML-predicted portfolios.

Initializing

Exercise

Tune random forest hyperparameters

As with all models, we want to optimize performance by tuning hyperparameters. We have many hyperparameters for random forests, but the most important is often the number of features we sample at each split, or max_features in RandomForestRegressor from the sklearn library. For models like random forests that have randomness built-in, we also want to set the random_state. This is set for our results to be reproducible.

Usually, we can use sklearn's GridSearchCV() method to search hyperparameters, but with a financial time series, we don't want to do cross-validation due to data mixing. We want to fit our models on the oldest data and evaluate on the newest data. So we'll use sklearn's ParameterGrid to create combinations of hyperparameters to search.

Instructions

100 XP
  • Set the n_estimators hyperparameter to be a list with one value (200) in the grid dictionary.
  • Set the max_features hyperparameter to be a list containing 4 and 8 in the grid dictionary.
  • Fit the random forest regressor model (rfr, already created for you) to the train_features and train_targets with each combination of hyperparameters, g, in the loop.
  • Calculate R\(^2\) by using rfr.score() on test_features and append the result to the test_scores list.