{"paper_id":"2506.17244","title":"Transformers Beyond Order: A Chaos-Markov-Gaussian Framework for Short-Term Sentiment Forecasting of Any Financial OHLC timeseries Data","authors":["Arif Pathan"],"paper_date":"2025-06-06","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2506.17244v1","page_url":"https://thequant.space/flowcharts/transformers-beyond-order-a-chaos-markov-gaussian-framework/","scores":{"empirical_rigor":6.5,"math_complexity":7,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes the Chaos‑Markov‑Gaussian (CMG) framework, a hybrid model that combines chaos theory, Markov modeling, Gaussian processes and transformer‑based deep learning for short‑term sentiment forecasting of OHLC time series.","quote":"In this paper, we introduce a new hybrid framework called CMG, which is short for Chaos–Markov–Gaussian.","summary":"Short-term sentiment forecasting in financial markets (e.g., stocks, indices) is challenging due to volatility, non-linearity, and noise in OHLC (Open, High, Low, Close) data. This paper introduces a novel CMG (Chaos-Markov-Gaussian) framework that integrates chaos theory, Markov property, and…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The model assumes the Markov property, i.e., future sentiment predictions depend only on the current market state.","type":"model","stated":"explicit","quote":"To support this mechanism, our data preprocessing pipeline ensures that each input instance retains only the current state, eliminating any leakage of information from previous time steps that could compromise the integrity of the Markov assumption."},{"assumption":"All models are trained and evaluated on the same preprocessed OHLC dataset without any feature engineering or manual adjustments.","type":"data","stated":"explicit","quote":"All methods are trained on the same dataset, with no feature engineering or manual adjustments, to ensure a fair comparison."}]},"datasets":{"status":"available","items":[{"name":"OHLC dataset of 160 market indices","provider":null,"kind":"market-prices","access":"unknown","period":"1+ years of 1 minute-level granularity","universe":"160 market indices across 16+ global financial markets","quote":"The dataset used in this study comprises OHLC (Open, High, Low, Close) data for 160 market indices randomly selected across 16+ global financial markets, ensuring wide coverage across regions, asset classes, and economic structures."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"intraday-bars"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"CMG achieves the highest average daybreak sentiment prediction accuracy of 0.7672 across 160 market indices, outperforming all baseline models.","kind":"predictive-accuracy","quote":"CMG 0.7672 ... LSTM 0.7605 ... BiLSTM 0.7602 ... GRU 0.7601 ... Logistic Regression 0.7562 ..."},{"finding":"Paired t‑tests show that CMG’s accuracy improvements over baselines are statistically significant (e.g., p=0.0063 vs. BiLSTM, p=0.0001 vs. Gaussian Naive Bayes).","kind":"statistical","quote":"CMG vs. BiLSTM 0.0063 ... CMG vs. Gaussian Naive Bayes 0.0001 ... CMG vs. GRU 0.0153 ..."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":16,"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":"2026-11-14T16:36:48Z"},"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/"}