Cryptocurrency Portfolio Optimization with Return Forecasting Using Deep Learning

سال انتشار: 1401
نوع سند: مقاله کنفرانسی
زبان: انگلیسی
مشاهده: 256

فایل این مقاله در 7 صفحه با فرمت PDF قابل دریافت می باشد

این مقاله در بخشهای موضوعی زیر دسته بندی شده است:

استخراج به نرم افزارهای پژوهشی:

لینک ثابت به این مقاله:

شناسه ملی سند علمی:

IPQCONF07_005

تاریخ نمایه سازی: 18 تیر 1401

چکیده مقاله:

In the cryptocurrency industry, portfolio management is frequently tough. Selecting assets from thousands, forecasting costs, calculating returns, and assessing risks are all difficult tasks. Our portfolio optimization solutions, on the other hand, assist in the implementation of an autonomous portfolio optimization system by providing short portfolio timeframes, the ability to acquire and analyze all essential data, and easy access to previous data. Furthermore, we use deep learning models, such as recurrent neural networks, to forecast the return on each cryptocurrency (RNN). Finally, we integrated classic MV and Sharpe portfolios with our deep projected return to address the portfolio optimization challenge. The analysis is based on three years of cryptocurrency data from ۲۰۱۸ to ۲۰۲۱. MV and Sharpe portfolio models with deep predicted returns, i.e., MV-DF and Sharpe-DF, beat standard models, according to experimental results.

نویسندگان

Mehrad Mashoof

Department of Industrial Engineering, Science and Research branch, Islamic Azad University, Tehran, Iran

Abbas Saghaei

Department of Industrial Engineering, Science and Research branch, Islamic Azad University, Tehran, Iran