{"paper_id":"2412.14529","title":"Leveraging Time Series Categorization and Temporal Fusion Transformers to Improve Cryptocurrency Price Forecasting","authors":["Arash Peik","Mohammad Ali Zare Chahooki","Amin Milani Fard","Mehdi Agha Sarram"],"paper_date":"2024-12-19","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2412.14529v1","page_url":"https://thequant.space/flowcharts/leveraging-time-series-categorization-and-temporal-fusion-tr/","scores":{"empirical_rigor":6,"math_complexity":7,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes categorizing financial time series into similar subseries and training a separate Temporal Fusion Transformer (TFT) model for each category.","quote":"In this work we propose to categorize the financial time series into several subseries with similar behavior and train a TFT model for each category of the subseries separately.","summary":"Organizing and managing cryptocurrency portfolios and decision-making on transactions is crucial in this market. Optimal selection of assets is one of the main challenges that requires accurate prediction of the price of cryptocurrencies. In this work, we categorize the financial time series into…","strategy":"category-based TFT with selector"},"assumptions":{"status":"available","items":[{"assumption":"The trading simulation assumes zero exchange fees.","type":"execution","stated":"explicit","quote":"In these transactions, we considered the 0 exchange fee."},{"assumption":"Financial covariates are excluded from the TFT models.","type":"model","stated":"explicit","quote":"In this comparison, we did not include financial covariates in any of the TFT models."}]},"datasets":{"status":"available","items":[{"name":"Binance 1-minute transaction data","provider":"Binance","kind":"market-prices","access":"proprietary","period":"2 years","universe":"cryptocurrency pairs","quote":"We collected a dataset of Binance transactions in 1-minute time frames for 2 years, which has not been published before at this granularity.","known_id":"binance"},{"name":"Binance 1-minute transaction data (testing)","provider":"Binance","kind":"market-prices","access":"proprietary","period":"18 months since December 2021","universe":"cryptocurrency pairs","quote":"We store transaction information of Binance exchange as the largest decentralized cryptocurrency exchange cumulatively in 1-minute time intervals for 18 months since December 2021.","known_id":"binance"}],"known":[{"id":"binance","name":"Binance","provider":"Binance","kind":"market-prices","access":"public","quote":"subseries) 17: end for 18: return {M,S} 3.1 Data Preprocessing We collected a dataset of Binance transactions in 1-minute time frames for 2 years, which has not been published before at this granularity.","mentions":3,"used_in":1}],"sample":{"start":null,"end":null,"market":"cryptocurrency","asset_class":"crypto","frequency":null},"data_resolution":"intraday-bars"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":false,"detail":null,"quote":"In these transactions, we considered the 0 exchange fee.","source":"front_matter","rule":"R3","candidates":{"front_matter":"no","evidence_card":"no","evidence_card_quoted":true},"card_detail":null,"card_quote":"In these transactions, we considered the 0 exchange fee.","meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"unclear","findings":[{"finding":"The proposed TFT models with time series categorization achieved more than 6% profit over two weeks, outperforming LSTM and non‑categorised transformers.","kind":"performance","quote":"our temporal fusion transformer models with time series categorization have created more than 6% more profit in 2 weeks."},{"finding":"If the category selector model achieved 100% accuracy, the strategy would turn 100 USDT into 248 USDT (148% profit) in two weeks.","kind":"performance","quote":"if the category selector model achieved 100% accuracy, a profit of 148% could be obtained."},{"finding":"With a selector accuracy of 79%, the method achieved a 3.16% profit over a two‑week period.","kind":"performance","quote":"with a selector accuracy of 79%, we achieved a profit of 3.16% over a two-week period."},{"finding":"The selector models achieved accuracies of 0.79 for the Markov chain selector and 0.74 for the LSTM selector.","kind":"predictive-accuracy","quote":"the accuracy of TFT model selector was 0.79 for Markov chain selector and 0.74 for LSTM selector."}],"reported_performance":{"strategy":"category-based TFT with selector","sharpe":null,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":25,"citations":{"cited_by_in_corpus":1,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":1},"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":"2026-11-14T17:49:02Z"},"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/"}