Detecting Signals for Stock Market Crashes - Machine Learning vs. Economic Models

Student: Fangmeyer David

Supervisor: Zinaida Avdeeva

Educational Programme: Big Data Systems (Master)

Year of Graduation: 2020

This thesis compares the ability to predict crashes using two different model groups. First, models that are backed economically, namely the Bond Stock Earnings Yield Differential (BSEYD) model and the Price Earnings ratio (P/E) model. Second, a machine learning approach including supervised learning techniques and recurrent neural networks (RNNs). The various models were applied on the S\&P500 and on the Spanish IBEX-35. Research showed that in some cases the machine learning techniques outperformed the economic models. Furthermore, 31 out of 34 models showed ex-ante crash signals for the latest COVID-19 related stock market crash.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses