كنفرانس بين المللی مهندسی صنايع و سيستم ها

صفحه اصلی / یازدهمین كنفرانس بين المللی مهندسی صنايع و سيستم ها

A Hybrid Prediction Model Based on Machine Learning and Random Walk Stochastic Processes in the Cryptocurrency market

نویسندگان :

Sana Aghajan navesi¹ Omid Hasanpour jesri² Ezatollah Abbasian³

1- دانشگاه تهران 2- دانشگاه تهران 3- دانشگاه تهران - دانشکدگان مدیریت - دانشکده مدیریت صنعتی و فناوری

کلمات کلیدی :

cryptocurrency،bitcoin،machin learning،stochastic process،random walk،technical analysis،fundamental analysis

چکیده :

The financial industry is becoming more and more depended on advanced computational technology in order to maintain competitiveness in a global economy. one of the recent branch of finance is forecasting of cryptocurrency values, which has significant impact on return on investment and profit growth in this area. The growth of cryptocurrencies and their global adoption have underscored the importance of employing advanced methods for analyzing these markets. Machine learning methods significantly improve the statistical accuracy of cryptocurrency return forecasts. This research aim is to predict cryptocurrency prices more accurately by proposing a hybrid model based on machine learning and random walk based stochastic process. The model integrates data from stochastic processes with technical and fundamental data to simulate the market’s unpredictable fluctuations. The performance of the proposed hybrid model will be compared to a machine learning model that only includes technical and fundamental data. This modeling is implemented by Python programming language. An improvement in the accuracy of predicting future cryptocurrency values is expected to be achieved by hybrid model. This research could improve making decision for investors, improve financial analysis tools, and assist in designing optimal investment portfolios.