Next Article in Journal
Accelerating Probabilistic Forecasting: A GPU-Based Approach to Reducing Computational Time
Previous Article in Journal
Modelling the RES Balanced Integration in Forecasting the Power System’s Long-Term Development
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Forecasting
Volume 8
Issue 4
10.3390/forecast8040065
forecasting-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Do Solana Exchange Flows Matter? Hypothesis-Driven Evidence from Short-Term SOL Direction Forecasting

by
Yan Egorov
,
Dmitry Grigoriev
*,
Daniil Zharikov
and
Anastasia Grigorieva
Center of Econometrics and Business Analytics, St. Petersburg State University, 199034 St. Petersburg, Russia
*
Author to whom correspondence should be addressed.
Forecasting 2026, 8(4), 65; https://doi.org/10.3390/forecast8040065
Submission received: 8 June 2026 / Revised: 22 July 2026 / Accepted: 29 July 2026 / Published: 30 July 2026
(This article belongs to the Section Forecasting in Economics and Management)
Browse Figures
Versions Notes

Abstract

This study examines whether centralized-exchange flows improve one-day-ahead forecasts of SOL return direction. Daily on-chain analysis (OCA) predictors are constructed from more than 41 million transfers above 1 SOL involving 101 labeled centralized-exchange hot wallets. Seven feature sets are evaluated using CatBoost, XGBoost, Random Forest, LSTM, and BiLSTM across four expanding-origin holdouts, with Elastic Net Logistic Regression as a linear benchmark. Technical analysis (TA) achieves the strongest average classification and transaction-cost-adjusted trading performance. OCA performs weakly alone and provides no stable average improvement when added to Baseline or TA. Selected flow- and volume-related subblocks outperform unrestricted OCA on individual descriptive metrics, but none achieves positive average trading performance. Observable Solana exchange flows therefore provide no robust standalone or incremental forecasting advantage beyond conventional predictors.
Keywords: Solana; cryptocurrency forecasting; on-chain analysis; exchange flows; direction forecasting; machine learning; trading strategies Solana; cryptocurrency forecasting; on-chain analysis; exchange flows; direction forecasting; machine learning; trading strategies

Share and Cite

MDPI and ACS Style

Egorov, Y.; Grigoriev, D.; Zharikov, D.; Grigorieva, A. Do Solana Exchange Flows Matter? Hypothesis-Driven Evidence from Short-Term SOL Direction Forecasting. Forecasting 2026, 8, 65. https://doi.org/10.3390/forecast8040065

AMA Style

Egorov Y, Grigoriev D, Zharikov D, Grigorieva A. Do Solana Exchange Flows Matter? Hypothesis-Driven Evidence from Short-Term SOL Direction Forecasting. Forecasting. 2026; 8(4):65. https://doi.org/10.3390/forecast8040065

Chicago/Turabian Style

Egorov, Yan, Dmitry Grigoriev, Daniil Zharikov, and Anastasia Grigorieva. 2026. "Do Solana Exchange Flows Matter? Hypothesis-Driven Evidence from Short-Term SOL Direction Forecasting" Forecasting 8, no. 4: 65. https://doi.org/10.3390/forecast8040065

APA Style

Egorov, Y., Grigoriev, D., Zharikov, D., & Grigorieva, A. (2026). Do Solana Exchange Flows Matter? Hypothesis-Driven Evidence from Short-Term SOL Direction Forecasting. Forecasting, 8(4), 65. https://doi.org/10.3390/forecast8040065

Article Metrics

Back to TopTop