Early Forecasting of Financial Asset and Local Market Movements Based on Multidimensional Market Factors Using Machine Learning Technologies
Abstract
This article focuses on the development and evaluation of machine learning models for early forecasting of asset
movement directions relative to a benchmark based on multidimensional market factors. It is shown that hybrid ML models integrating temporal, cross-market, and structural features make it possible to generate robust signals of market regime
changes. The practical applicability of the results is demonstrated not only for financial analysis but also for the real estate
development sector: early identification of market rotation phases improves housing demand forecasting, allows for adjustments in marketing strategies, supports the assessment of mortgage capital availability dynamics, and facilitates construction volume planning. The findings expand the analytical toolkit of the Russian housing market and strengthen the capacity
to forecast buyer behavior and investment activity.
References
- Акуста А. Analysis of the Relationship Between Cross Capital Flows and Stock Exchange Index with Machine Learning
- // Abant Sosyal Bilimler Dergisi. 2024.
- Бутер Д. Forecasting project Cost Flow using Machine Learning // Международный журнал экономических исследований. 2020.
- Вельмуруган Д.К., Мира Т., Миначи Р. Stock Market Prediction using Machine Learning Algorithms // International
- Journal of Advanced Research in Science, Communication and Technology. 2022.
- Гаде С.Г., Сайяд Ш.Ф. Enhancing Stock Market Prediction with ARIMA and Machine Learning // Proceeding International
- Conference on Science and Engineering. 2023.
- Гонсалес Рохас К. Foreign Exchange Forecasting via Machine Learning // Международный журнал экономического
- анализа. 2018.
- Дербенцев В., Даценко Н., Степаненко О., Безкоровайный В. Forecasting Cryptocurrency Prices Time Series Using
- Machine Learning // Международный журнал финансовых исследований. 2019.
- Дербенцев В., Матвийчук А., Даценко Н., Безкоровайный В., Азарян А. Machine learning approaches for financial time
- series forecasting // Advanced Studies of Financial Technologies and Cryptocurrency Markets. 2020.
- Леперс Э., Меркадо Р.В. Analysing sectoral capital flows // OECD Working Papers on International Investment. 2021.
- Ма Т., Ке Г. Multi-task Learning for Financial Forecasting // ArXiv. 2018.
Statistics
Article Sidebar
Article Details
Issue
Section
Publication History
How to Cite
License
Copyright (c) 2026 Денис Андреевич Сериков, Сергей Сергеевич Можогин, Александр Александрович Воронов
This work is licensed under a Creative Commons Attribution 4.0 International License.