Macro3M

Macro3M uses mathematical statistics and machine learning models to analyze the impact of U.S. economic indicators on the market, find the rules and build a generalized model. Through the model, you can enter specific economic indicator data to predict the market performance next month. You can use the predicted value of the model to help you analyze the impact of economic indicators on the market. In the long run, the market always fluctuates around the economy and tends to the same direction.

Economic Activity:
Economic indicators are statistics about economic activity. These indicators help analyze the overall performance of the economy. The dataset used by Macro3M contains 22 US economic indicators from 1962 to 2020. After analyzing through statistical tools, six of these indicators are highly correlated with the US market. The six indicators are Nonfarm payroll employment, Commercial and industrial loans, Personal income, M2 money stock, Industrial production index and Producer price index.

Algorithms and Models:
Macro3M uses three deep learning algorithms (Multilayer Perceptron, Recurrent Neural Network, Long Short-Term Memory) to establish three generalization models. The evaluation metrics of these models is to minimize the mean absolute error (MAE) between the predicted value and the target value. In machine learning, our goal is to obtain a generalizable model that performs well on data that has never been seen before. Macro3M has tracked the MAE performance of nine machine learning models for a long time, and the final results show that the deep learning model is better than the traditional machine learning model.