{"paper_id":"2601.14062","title":"Demystifying the trend of the healthcare index: Is historical price a key driver?","authors":["Payel Sadhukhan","Samrat Gupta","Subhasis Ghosh","Tanujit Chakraborty"],"paper_date":"2026-01-20","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2601.14062v1","page_url":"https://thequant.space/flowcharts/demystifying-the-trend-of-the-healthcare-index-is-historica/","scores":{"empirical_rigor":5,"math_complexity":5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a supervised classification model that uses original OHLC prices, volatility indicators, and novel nowcasting features derived from mutual OHLC ratios to predict the next day's opening index.","quote":"... The problem is formulated as a supervised classification task involving a one-step-ahead rolling window. A diverse feature set is constructed, comprising original prices, volatility-based technical indicators, and a novel class of nowcasting features derived from mutual OHLC ratios.","summary":"Healthcare sector indices consolidate the economic health of pharmaceutical, biotechnology, and healthcare service firms. The short-term movements in these indices are closely intertwined with capital allocation decisions affecting research and development investment, drug availability, and…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Class labels are defined by comparing the current day's index values with the open index of the next trading day.","type":"data","stated":"explicit","quote":"Day t’s class label is derived by comparing its index (open/ high/ low/ close) with the open index of the next trading day (t + 1)."},{"assumption":"The first 19 days are excluded because historical feature calculation requires a 20‑day window.","type":"data","stated":"explicit","quote":"The calculation of historical features requires a window of 20 days, out of which 19 days are before the day of calculation. Hence, we have to exclude the initial 19 days from our calculation."},{"assumption":"A rolling one‑step‑ahead prediction framework is used rather than multi‑step forecasting.","type":"model","stated":"explicit","quote":"We have incorporated one-step-ahead rolling window approach for prediction instead of multi-step-ahead forecasting"},{"assumption":"The first 80 % of chronological observations are used for training and the remaining 20 % for testing.","type":"data","stated":"explicit","quote":"The first 80% days are considered for training the model, and the remaining 20% are used to test the model."},{"assumption":"The feature set remains the same across all four sub‑problems; only the target class changes.","type":"model","stated":"explicit","quote":"Note that, depending on ∗, the dataset changes. The change happens due to the change in the target class only; the feature set remains the same across all cases."}]},"datasets":{"status":"available","items":[{"name":"Healthcare index – S&P 500 (U.S.A.)","provider":"public OHLC data","kind":"market-prices","access":"public","period":"Apr 1, 2019 – Mar 31, 2024","universe":"Healthcare sector index","quote":"Period Apr 1, 2019 – Mar 31, 2024 ... No. of trading days 1256"}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"n/a","evidence_card":"unclear","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"The models consistently achieved MCC scores greater than 0.6 and accuracy scores greater than 0.8 on held‑out test data.","kind":"predictive-accuracy","quote":"The models consistently achieved MCC scores greater than 0.6 and accuracy scores greater than 0.8 on the held-out test data"},{"finding":"Nowcasting features substantially improve prediction performance, delivering the highest accuracy and MCC across three of four sub‑problems.","kind":"performance","quote":"The results show that the addition of nowcasting features has elevated the correctness of predictions. For three of the four sub-problems, it has achieved substantial improvements; both accuracy and MCC scores have"},{"finding":"Volatility‑based technical indicators (Donchian Channel, Bollinger Bands, Keltner Channels) show inconsistent or negligible correlation with the rise/fall of the open index.","kind":"negative","quote":"... have failed to show consistent correlation with the rise/ fall of indices."},{"finding":"Raw original price features provide moderate but inconsistent predictive utility compared to nowcasting features.","kind":"performance","quote":"In contrast, historical price movement exhibits negligible predictive association with the directional movement of the opening index, while raw index values offer moderate but inconsistent predictive utility."},{"finding":"Shapley‑based explainability confirms that nowcasting features are the dominant contributors, followed by original prices.","kind":"statistical","quote":"... outcomes reveal the dominant role of the nowcasting features, followed by a more moderate contribution of original prices."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[{"paper":{"paper_id":"2412.15448","title":"Risk-Adjusted Performance of Random Forest Models in High-Frequency Trading","paper_date":"2024-12-19","authors":["Akash Deep","Abootaleb Shirvani","Chris Monico","Svetlozar Rachev","Frank J. Fabozzi"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/risk-adjusted-performance-of-random-forest-models-in-high-fr/"},"question":"Do price‑based features provide predictive utility for the target variable?","this_paper_finding":"Raw original price features provide moderate but inconsistent predictive utility compared to nowcasting features.","other_paper_finding":"Primary price‑based features account for over 60% of feature importance, while technical indicators contribute only 14%–15%.","other_paper_quote":"A feature importance analysis demonstrates that primary price‑based features dominate the predictions made by the model, accounting for over 60% of the importance, while established technical indicators, such as RSI and Bollinger Bands, account for only 14%--15%","note":"A finds price features account for >60% importance, B finds raw price offers moderate but inconsistent utility versus nowcasting features.","confidence":0.536}],"compared_with":51,"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":"2026-11-14T17:15:32Z"},"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/"}