{"paper_id":"2508.03910","title":"Comparing Normalization Methods for Portfolio Optimization with Reinforcement Learning","authors":["Caio de Souza Barbosa Costa","Anna Helena Reali Costa"],"paper_date":"2025-08-05","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2508.03910v1","page_url":"https://thequant.space/flowcharts/comparing-normalization-methods-for-portfolio-optimization-w/","scores":{"empirical_rigor":6,"math_complexity":5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper evaluates two common state‑normalization methods versus normalizing input data across three markets and shows that normalizing the data, not the RL state, improves portfolio‑optimization performance.","quote":"This article demonstrates empirically that, in the portfolio optimization domain, to normalize the input data instead of the RL agent’s state improves the performance of the agent not only in the stock market but also in the cryptocurrency market.","summary":"Recently, reinforcement learning has achieved remarkable results in various domains, including robotics, games, natural language processing, and finance. In the financial domain, this approach has been applied to tasks such as portfolio optimization, where an agent continuously adjusts the…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The agent is trained on historical daily price data from 2011‑11‑11 to 2019‑12‑31 and tested on the calendar year 2020.","type":"market","stated":"explicit","quote":"In the NYSE and IBOVESPA portfolios, the agent is trained in the period between 2011/11/11 and 2019/12/31 and tested in the year of 2020 (from January 1st to December 31st)."},{"assumption":"A flat commission fee of 0.25 % is applied on each rebalancing transaction.","type":"execution","stated":"explicit","quote":"Commission rate 0.0025 Rate of comission fee applied when rebalancing the portfolio."},{"assumption":"State representation uses a time window of 50 steps.","type":"model","stated":"explicit","quote":"Time window 50 Size (in steps) of the time window considered in the state representation."},{"assumption":"The markets considered are NYSE (stable), IBOVESPA (more volatile), and a cryptocurrency basket (most volatile).","type":"market","stated":"explicit","quote":"In comparison to NYSE, this market is considerably more volatile."},{"assumption":"Daily closing, high and low prices are sufficient to represent the market state.","type":"data","stated":"implied","quote":"In both cases, the data is composed of daily closing, high and low prices of the components of the portfolio."}]},"datasets":{"status":"available","items":[{"name":"NYSE and IBOVESPA daily price data","provider":"Yahoo Finance","kind":"market-prices","access":"public","period":null,"universe":"NYSE stocks and IBOVESPA constituents","quote":"For NYSE and IBOVESPA, the price of the stocks is taken from Yahoo Finance website.","known_id":"yahoo-finance"},{"name":"Cryptocurrency daily price dataset","provider":"Kaggle","kind":"market-prices","access":"public","period":null,"universe":"9 cryptocurrency coins (ADA, BNB, BTC, BTG, DOGE, ETH, LINK, TRX, XRP)","quote":"The cryptocurrencies’ historical prices, on the other hand, were obtained from a dataset available in Kaggle.","known_id":"kaggle"}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"For NYSE and IBOVESPA, the price of the stocks is taken from Yahoo Finance website1.","mentions":2,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":null,"detail":"A flat commission fee of 0.25 % per trade is applied when rebalancing the portfolio.","quote":"Commission rate 0.0025 Rate of comission fee applied when rebalancing the portfolio.","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"A flat commission fee of 0.25 % per trade is applied when rebalancing the portfolio.","card_quote":"Commission rate 0.0025 Rate of comission fee applied when rebalancing the portfolio.","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"State normalization can degrade the RL agent’s performance, while normalizing the input data consistently yields higher final accumulative portfolio values across all three markets.","kind":"performance","quote":"The results indicate that, in this specific domain, the state normalization can indeed degrade the agent’s performance."},{"finding":"Data normalization achieved the highest max FAPV in NYSE (1.74), IBOVESPA (2.47) and Crypto (2.23) compared to other normalization variants.","kind":"performance","quote":"TABLE V MAX FAPV FOR EACH MARKET AND NORMALIZATION METHOD."},{"finding":"More volatile markets benefit more from data normalization, as the agent avoids information loss inherent to state‑normalization methods.","kind":"performance","quote":"The results of the experiments showed that the more volatile a market is, the more it benefits from the usage of the data normalization since the agent does not suffer from the information loss inherent to the state normalization methods."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":13,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T17:30:33Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}