Modeling Stock Price Changes Based on Microstructural Market Data

In modern electronic stock exchanges there is an opportunity to analyze event driven market microstructure data. This data is highly informative and describes physical price formation which makes it possible to find complex patterns in price dynamics. It is very time consuming and hard to find this...

Full description

Saved in:
Bibliographic Details
Main Author: N. A.  Bilev
Format: Article
Language:Russian
Published: Government of the Russian Federation, Financial University 2018-11-01
Series:Финансы: теория и практика
Subjects:
Online Access:https://financetp.fa.ru/jour/article/view/757
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850025777029971968
author N. A.  Bilev
author_facet N. A.  Bilev
author_sort N. A.  Bilev
collection DOAJ
description In modern electronic stock exchanges there is an opportunity to analyze event driven market microstructure data. This data is highly informative and describes physical price formation which makes it possible to find complex patterns in price dynamics. It is very time consuming and hard to find this kind of patterns by handcrafted rules. However, modern machine learning models are able to solve such issues automatically by learning price behavior which is always changing. The present study presents profitable trading system based on a machine learning model and market microstructure data. Data for the research was collected from Moscow stock exchange MICEX and represents a limit order book change log and all market trades of a liquid security for a certain period. Logistic regression model was used and compared to neural network models with different configuration. According to the study results logistic regression model has almost the same prediction quality as neural network models have but also has a high speed of response which is very important for stock market trading. The developed trading system has medium frequency of deals submission that lets it to avoid expensive infrastructure which is usually needed in high-frequency trading systems. At the same time, the system uses the potential of high quality market microstructure data to the full extent. This paper describes the entire process of trading system development including feature engineering, models behavior comparison and creation of trading strategy with testing on historical data.
format Article
id doaj-art-e36f28c01aea47baab82067ea0c05ed9
institution DOAJ
issn 2587-5671
2587-7089
language Russian
publishDate 2018-11-01
publisher Government of the Russian Federation, Financial University
record_format Article
series Финансы: теория и практика
spelling doaj-art-e36f28c01aea47baab82067ea0c05ed92025-08-20T03:00:44ZrusGovernment of the Russian Federation, Financial UniversityФинансы: теория и практика2587-56712587-70892018-11-0122514115310.26794/2587-5671-2018-22-5-141-153682Modeling Stock Price Changes Based on Microstructural Market DataN. A.  Bilev0Lomonosov Moscow State university, MosocowIn modern electronic stock exchanges there is an opportunity to analyze event driven market microstructure data. This data is highly informative and describes physical price formation which makes it possible to find complex patterns in price dynamics. It is very time consuming and hard to find this kind of patterns by handcrafted rules. However, modern machine learning models are able to solve such issues automatically by learning price behavior which is always changing. The present study presents profitable trading system based on a machine learning model and market microstructure data. Data for the research was collected from Moscow stock exchange MICEX and represents a limit order book change log and all market trades of a liquid security for a certain period. Logistic regression model was used and compared to neural network models with different configuration. According to the study results logistic regression model has almost the same prediction quality as neural network models have but also has a high speed of response which is very important for stock market trading. The developed trading system has medium frequency of deals submission that lets it to avoid expensive infrastructure which is usually needed in high-frequency trading systems. At the same time, the system uses the potential of high quality market microstructure data to the full extent. This paper describes the entire process of trading system development including feature engineering, models behavior comparison and creation of trading strategy with testing on historical data.https://financetp.fa.ru/jour/article/view/757stock market tradingalgorithmic tradingmarket microstructurelimit order bookmachine learningtime seriesinvestmentcapital management
spellingShingle N. A.  Bilev
Modeling Stock Price Changes Based on Microstructural Market Data
Финансы: теория и практика
stock market trading
algorithmic trading
market microstructure
limit order book
machine learning
time series
investment
capital management
title Modeling Stock Price Changes Based on Microstructural Market Data
title_full Modeling Stock Price Changes Based on Microstructural Market Data
title_fullStr Modeling Stock Price Changes Based on Microstructural Market Data
title_full_unstemmed Modeling Stock Price Changes Based on Microstructural Market Data
title_short Modeling Stock Price Changes Based on Microstructural Market Data
title_sort modeling stock price changes based on microstructural market data
topic stock market trading
algorithmic trading
market microstructure
limit order book
machine learning
time series
investment
capital management
url https://financetp.fa.ru/jour/article/view/757
work_keys_str_mv AT nabilev modelingstockpricechangesbasedonmicrostructuralmarketdata