{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T06:34:30Z","timestamp":1762842870347,"version":"build-2065373602"},"reference-count":42,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T00:00:00Z","timestamp":1762819200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100031478","name":"NextGenerationEU","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100031478","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>The Counter-Strike 2 skin market has developed into a multi-billion-dollar digital asset ecosystem, characterized by high volatility, low liquidity, and pricing inefficiencies that differ substantially from traditional financial markets. Despite the growing economic relevance of virtual items, no previous study has systematically examined the use of artificial intelligence for skin trading.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This work designs and evaluates an automated trading system that applies deep learning models, specifically Long Short-Term Memory networks and Neural Hierarchical Interpolation for Time Series, to forecast skin prices and guide trading decisions. A dataset of 12,000 unique skins from the Steam Market, covering the period from May 2024 to April 2025, was collected using the CSGOskins.gg application programming interface. To reflect real market conditions, the trading strategy incorporated the Steam Market restrictions of a seven-day minimum holding period and a ten percent transaction cost, and was benchmarked against a traditional buy-and-hold strategy. Backtesting was performed multiple time horizons of two, three, and 6 months. Portfolio selection was based on risk and return criteria, including a Sharpe ratio greater than one, a Sortino ratio greater than two, and a return on investment above five percent.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Artificial intelligence consistently outperforms buy-and-hold, particularly in smaller, more concentrated portfolios and over longer time horizons. For example, in 6-month simulations, artificial intelligence portfolios achieved returns approaching 20%, compared to 5% to 10% for buy-and-hold, with excess returns as high as 75% in small portfolios. Larger portfolios reduced absolute returns but improved risk-adjusted performance, confirming that diversification enhances stability while diluting raw profitability. Analysis of portfolio composition by rarity further revealed that artificial intelligence favors moderately rare and liquid skins such as Mil-Spec, resembling mid-cap equity investment strategies, while buy-and-hold accumulates rarer skins, analogous to small-cap holdings that rely on scarcity premiums.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>These findings highlight that even in virtual goods markets, the trade-offs between return, risk, and diversification reflect established principles of modern portfolio theory. The study demonstrates both the feasibility and the potential of artificial intelligence-based trading systems in the Counter-Strike 2 skin economy, contributing methodological advances and practical insights for participants in this emerging digital asset market.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2025.1702924","type":"journal-article","created":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T06:31:53Z","timestamp":1762842713000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Artificial intelligence for algorithmic trading digital assets: evidence from the Counter-Strike 2 skin market"],"prefix":"10.3389","volume":"8","author":[{"given":"Federico","family":"Guede-Fern\u00e1ndez","sequence":"first","affiliation":[]},{"given":"Yash","family":"Wagle","sequence":"additional","affiliation":[]},{"given":"Pedro","family":"Dias","sequence":"additional","affiliation":[]},{"given":"Ana Paula","family":"Giordano","sequence":"additional","affiliation":[]},{"given":"L\u00facio","family":"Henriques","sequence":"additional","affiliation":[]},{"given":"Gon\u00e7alo","family":"Costa","sequence":"additional","affiliation":[]},{"given":"Salom\u00e9","family":"Azevedo","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2025,11,11]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"428","DOI":"10.3390\/a15110428","article-title":"Applying artificial intelligence in cryptocurrency markets: a survey","volume":"15","author":"Amirzadeh","year":"2022","journal-title":"Algorithms"},{"key":"B2","doi-asserted-by":"publisher","first-page":"e0242600","DOI":"10.1371\/journal.pone.0242600","article-title":"Behavioral structure of users in cryptocurrency market","volume":"16","author":"Aspembitova","year":"2021","journal-title":"PLoS ONE"},{"key":"B3","doi-asserted-by":"publisher","first-page":"185336","DOI":"10.1109\/ACCESS.2024.3514512","article-title":"Development of a hybrid recommendation system for nfts using deep learning techniques","volume":"12","author":"Aydo\u011fdu","year":"2024","journal-title":"IEEE Access"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1814759","DOI":"10.1155\/2022\/1814759","article-title":"Determining the pricing strategy and pricing the products of mobile games: mathematical model approach","volume":"2022","author":"Budak","year":"2022","journal-title":"Wireless Commun. Mobile Comput"},{"key":"B5","doi-asserted-by":"publisher","first-page":"6989","DOI":"10.1609\/aaai.v37i6.25854","article-title":"Nhits: neural hierarchical interpolation for time series forecasting","volume":"37","author":"Challu","year":"2023","journal-title":"Proc. AAAI Conf. Artif. Intell"},{"key":"B6","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1016\/j.clsr.2011.05.007","article-title":"How virtual are virtual economies? An exploration into the legal, social and economic nature of virtual world economies","volume":"27","author":"Chambers","year":"2011","journal-title":"Comput. Law Security Rev"},{"key":"B7","doi-asserted-by":"publisher","first-page":"104109","DOI":"10.1016\/j.jfineco.2025.104109","article-title":"Diversification driven demand for large stock","volume":"172","author":"Chen","year":"2025","journal-title":"J. Fin. Econ"},{"key":"B8","doi-asserted-by":"publisher","first-page":"526","DOI":"10.3390\/jrfm14110526","article-title":"Application of artificial intelligence in stock market forecasting: a critique, review, and research agenda","volume":"14","author":"Chopra","year":"2021","journal-title":"J. Risk Fin. Manag"},{"key":"B9","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/S0304-405X(99)00057-4","article-title":"Commonality in liquidity","volume":"56","author":"Chordia","year":"2000","journal-title":"J. Fin. Econ"},{"key":"B10","doi-asserted-by":"publisher","first-page":"105700","DOI":"10.1016\/j.jbankfin.2019.105700","article-title":"Liquidity risk and expected option returns","volume":"111","author":"Choy","year":"2020","journal-title":"J. Banking Fin"},{"key":"B11","doi-asserted-by":"publisher","first-page":"102015","DOI":"10.1016\/j.jksuci.2024.102015","article-title":"Artificial intelligence techniques in financial trading: a systematic literature review","volume":"36","author":"Dakalbab","year":"2024","journal-title":"J. King Saud Univ"},{"key":"B12","author":"D'Anastasio","year":"2025","journal-title":"Market for \u2018Counter-Strike 2' Digital Items Hits New High"},{"key":"B13","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1145\/3588155.3588181","article-title":"\u201cNft appraisal using machine learning,\u201d","volume-title":"Proceedings of the 2023 5th Asia Pacific Information Technology Conference","author":"Dawod","year":"2023"},{"key":"B14","doi-asserted-by":"publisher","first-page":"102097","DOI":"10.1016\/j.frl.2021.102097","article-title":"Is non-fungible token pricing driven by cryptocurrencies?","volume":"44","author":"Dowling","year":"2022","journal-title":"Fin. Res. Lett"},{"key":"B15","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1016\/j.ejor.2017.11.054","article-title":"Deep learning with long short-term memory networks for financial market predictions","volume":"270","author":"Fischer","year":"2018","journal-title":"Eur. J. Operat. Res"},{"key":"B16","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.chb.2017.01.042","article-title":"Why do people buy virtual goods: a meta-analysis","volume":"71","author":"Hamari","year":"2017","journal-title":"Comput. Hum. Behav"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput"},{"key":"B18","doi-asserted-by":"publisher","first-page":"103007","DOI":"10.1016\/j.frl.2022.103007","article-title":"Price determinants of non-fungible tokens in the digital art market","volume":"48","author":"Horky","year":"2022","journal-title":"Fin. Res. Lett"},{"key":"B19","doi-asserted-by":"publisher","first-page":"795","DOI":"10.1177\/10591478241231854","article-title":"Sponsored product-based competition and customer engagement: a study of an esports competition in the video game industry","volume":"33","author":"Jo","year":"2024","journal-title":"Prod. Operat. Manag"},{"key":"B20","doi-asserted-by":"publisher","first-page":"33","DOI":"10.2307\/1913643","article-title":"Regression quantiles","volume":"46","author":"Koenker","year":"1978","journal-title":"Econometrica"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1267","DOI":"10.1002\/mar.21816","article-title":"A meta-analysis on the effects of product scarcity","volume":"40","author":"Ladeira","year":"2023","journal-title":"Psychol. Market"},{"key":"B22","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1007\/s10660-009-9028-2","article-title":"Virtual item sales as a revenue model: identifying attributes that drive purchase decisions","volume":"9","author":"Lehdonvirta","year":"2009","journal-title":"Electr. Commerce Res"},{"key":"B23","doi-asserted-by":"publisher","first-page":"100864","DOI":"10.1016\/j.ssaho.2024.100864","article-title":"Stock market prediction using artificial intelligence: a systematic review of systematic reviews","volume":"9","author":"Lin","year":"2024","journal-title":"Soc. Sci. Hum. Open"},{"key":"B24","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/SSCI.2017.8280814","article-title":"\u201cLiquidity risk and asset movement evidence from brexit,\u201d","volume-title":"2017 IEEE Symposium Series on Computational Intelligence (SSCI)","author":"Mago","year":"2017"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1087","DOI":"10.1287\/mnsc.22.10.1087","article-title":"Scoring rules for continuous probability distributions","volume":"22","author":"Matheson","year":"1976","journal-title":"Manag. Sci"},{"key":"B26","doi-asserted-by":"publisher","first-page":"20902","DOI":"10.1038\/s41598-021-00053-8","article-title":"Mapping the nft revolution: market trends, trade networks, and visual features","volume":"11","author":"Nadini","year":"2021","journal-title":"Sci. Rep"},{"key":"B27","doi-asserted-by":"crossref","first-page":"1419","DOI":"10.1109\/IJCNN.2017.7966019","article-title":"\u201cStock market's price movement prediction with lstm neural networks,\u201d","volume-title":"2017 International Joint Conference on Neural Networks (IJCNN)","author":"Nelson","year":"2017"},{"key":"B28","doi-asserted-by":"publisher","first-page":"117017","DOI":"10.1016\/j.eswa.2022.117017","article-title":"An automated cryptocurrency trading system based on the detection of unusual price movements with a time-series clustering-based approach","volume":"200","author":"Ozer","year":"2022","journal-title":"Expert Syst. Applic"},{"key":"B29","doi-asserted-by":"publisher","first-page":"642","DOI":"10.1086\/374184","article-title":"Liquidity risk and expected stock returns","volume":"111","author":"P\u00e1stor","year":"2003","journal-title":"J. Polit. Econ."},{"key":"B30","doi-asserted-by":"publisher","first-page":"107670","DOI":"10.1016\/j.frl.2025.107670","article-title":"Skin in the game: the returns of digital assets from computer games","volume":"83","author":"Reichenbach","year":"2025","journal-title":"Fin. Res. Lett"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.62177\/apemr.v2i2.210","article-title":"Deep learning for stock performance prediction: a sharpe ratio-optimized approach","author":"Sch\u00e4fer","year":"2025","journal-title":"Asia Pac. Econ. Manag. Rev"},{"key":"B32","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1086\/294846","article-title":"Mutual fund performance","volume":"39","author":"Sharpe","year":"1966","journal-title":"J. Business"},{"key":"B33","doi-asserted-by":"crossref","first-page":"1394","DOI":"10.1109\/ICMLA.2018.00227","article-title":"\u201cA comparison of arima and lstm in forecasting time series,\u201d","volume-title":"2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA)","author":"Siami-Namini","year":"2018"},{"key":"B34","first-page":"2951","author":"Snoek","year":"2012"},{"key":"B35","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1007\/s10462-024-10989-8","article-title":"Deep learning-based time series forecasting","volume":"58","author":"Song","year":"2024","journal-title":"Artif. Intell. Rev"},{"key":"B36","doi-asserted-by":"crossref","first-page":"444","DOI":"10.5220\/0010392804440453","article-title":"\u201cMeasuring inflation within virtual economies using deep reinforcement learning,\u201d","volume-title":"Proceedings of the 13th International Conference on Agents and Artificial Intelligence","author":"Stephens","year":"2021"},{"key":"B37","doi-asserted-by":"publisher","first-page":"1308","DOI":"10.1108\/EJM-09-2016-0510","article-title":"Product market diversification and market emphasis","volume":"51","author":"Sun","year":"2017","journal-title":"Eur. J. Market"},{"key":"B38","doi-asserted-by":"publisher","first-page":"1371502","DOI":"10.3389\/frai.2024.1371502","article-title":"Enhancing portfolio management using artificial intelligence: literature review","volume":"7","author":"Sutiene","year":"2024","journal-title":"Front. Artif. Intell"},{"key":"B39","doi-asserted-by":"publisher","first-page":"596","DOI":"10.1007\/11752912_77","article-title":"\u201cAn intelligent statistical arbitrage trading system,\u201d","author":"Thomaidis","year":"2006","journal-title":"Advances in Artificial Intelligence"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1332\/policypress\/9781529223040.003.0001","author":"Thorhauge","year":"2023","journal-title":"Games in the Platform Economy: Steam's Tangled Markets, 1st Edn"},{"key":"B41","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1177\/1469540521993929","article-title":"Epic, steam, and the role of skin-betting in game (platform) economies","volume":"21","author":"Thorhauge","year":"2021","journal-title":"J. Cons. Cult"},{"key":"B42","doi-asserted-by":"publisher","first-page":"7671","DOI":"10.1109\/TCSS.2024.3430846","article-title":"An advanced pricing mechanism for nonfungible tokens (nfts) based on rarity and market dynamics","volume":"11","author":"Xiong","year":"2024","journal-title":"IEEE Trans. Comput. Soc. Syst"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1702924\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T06:31:55Z","timestamp":1762842715000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1702924\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,11]]},"references-count":42,"alternative-id":["10.3389\/frai.2025.1702924"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1702924","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,11]]},"article-number":"1702924"}}