{"paper_id":"2505.19243","title":"Comparative analysis of financial data differentiation techniques using LSTM neural network","authors":["Dominik Stempień","Janusz Gajda"],"paper_date":"2025-05-25","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2505.19243v1","page_url":"https://thequant.space/flowcharts/comparative-analysis-of-financial-data-differentiation-techn/","scores":{"empirical_rigor":8,"math_complexity":6.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes using fractional differentiation methods as data transformations to improve LSTM forecasting performance and construct profitable trading strategies.","quote":"The findings suggest that fractional differentiation methods provide a suitable data transformation technique, improving the predictive model forecasting performance.","summary":"We compare traditional approach of computing logarithmic returns with the fractional differencing method and its tempered extension as methods of data preparation before their usage in advanced machine learning models. Differencing parameters are estimated using multiple techniques. The empirical…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Many econometric time-series models and supervised machine learning algorithms require data stationarity.","type":"statistical","stated":"explicit","quote":"Many econometric time-series models and supervised machine learning algorithms require data stationarity in order to correctly forecast unobserved values."},{"assumption":"Trading signals are only acted upon when potential gains exceed transaction costs.","type":"execution","stated":"explicit","quote":"opening a new position or modifying an existing one takes place only if potential gains associated with a trade exceed transaction costs."},{"assumption":"The ARFIMA model can extract linear patterns from price series before feeding residuals to the LSTM.","type":"model","stated":"explicit","quote":"the ARFIMA model can extract linear patterns from data."},{"assumption":"Fractional differentiation parameters are estimated using multiple techniques and the smallest value achieving stationarity may not yield the best predictions.","type":"model","stated":"explicit","quote":"the smallest possible value of the differencing operator that achieves stationarity does not always lead to the most reliable predictions."}]},"datasets":{"status":"available","items":[{"name":"Four major stock indices","provider":"Yahoo Finance (S&P 500, DAX, Nikkei 225) and Stooq (WIG20)","kind":"market-prices","access":"public","period":"01.01.2014 to 31.12.2023","universe":"S&P 500, WIG20, DAX, Nikkei 225","quote":"Data was downloaded from two sources: Yahoo Finance with the use of Python’s yfinance library (S&P 500, DAX, and Nikkei 225) and the Stooq portal (WIG20).","known_id":"yahoo-finance"}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"Data was downloaded from two sources: Yahoo Finance with the use of Python’s yfinance library (S&P 500, DAX, and Nikkei 225) and the Stooq portal (WIG20).","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":"Transaction costs of 0.005% are included in the backtesting results.","quote":"Transaction costs of 0.005% are included (Kryńska and Ślepaczuk, 2022).","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Transaction costs of 0.005% are included in the backtesting results.","card_quote":"Transaction costs of 0.005% are included (Kryńska and Ślepaczuk, 2022).","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Fractional differentiation techniques outperform other data preparation methods and the Buy & Hold benchmark for both Long‑Short and Long‑Only strategies.","kind":"performance","quote":"The presented results strongly indicate that fractional differentiation techniques outperform not only the rest of the methods, but also the benchmark 𝐵𝑢𝑦 & 𝐻𝑜𝑙𝑑 approach."},{"finding":"LSTM models trained on fractionally differentiated data achieve higher forecasting accuracy than those using logarithmic returns.","kind":"predictive-accuracy","quote":"Based on the forecasting accuracy metrics, the LSTM models trained on fractionally differentiated data provided more accurate predictions compared to those using logarithmic returns."},{"finding":"Trading performance metrics confirm the superiority of memory‑preserving (fractionally differentiated) inputs.","kind":"performance","quote":"Trading performance metrics further confirmed the superiority of fractionally differentiated data, that is, memory-preserving techniques, as inputs to the predictive model."},{"finding":"Fractional differencing with tempering removes excessive memory, leading to poorer forecasting and trading results.","kind":"negative","quote":"Fractional differencing with tempering appeared to constitute an approach that tends to remove an excessive amount of memory from the time‑series, which negatively affected both forecasting accuracy and trading model performance."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":19,"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":"2026-11-14T17:37:09Z"},"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/"}