{"paper_id":"2506.03153","title":"Why Regression? Binary Encoding Classification Brings Confidence to Stock Market Index Price Prediction","authors":["Junzhe Jiang","Chang Yang","Xinrun Wang","Bo Li"],"paper_date":"2025-05-18","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2506.03153v1","page_url":"https://thequant.space/flowcharts/why-regression-binary-encoding-classification-brings-confid/","scores":{"empirical_rigor":6,"math_complexity":6.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes CUBIC, an end‑to‑end framework that fuses constituent stocks in latent space, uses binary‑encoding classification, and adds confidence‑guided prediction and trading.","quote":"we propose CUBIC, a novel end-to-end framework that explicitly models the adaptive fusion of constituent stocks for index price prediction.","summary":"Stock market indices serve as fundamental market measurement that quantify systematic market dynamics. However, accurate index price prediction remains challenging, primarily because existing approaches treat indices as isolated time series and frame the prediction as a simple regression task.…","strategy":"CUBIC"},"assumptions":{"status":"available","items":[{"assumption":"A flat transaction cost of 0.1% per trade is applied to all trading results.","type":"execution","stated":"explicit","quote":"We consider a transaction cost of 0.1% for each trade."},{"assumption":"The binary encoding of target values provides a robust alternative to continuous regression.","type":"model","stated":"explicit","quote":"since regression tasks are challenging due to continuous value estimation, we reformulate the regression into the classification task, where the target value is converted to binary and we optimize the prediction of the value of each digit with cross-entropy loss."},{"assumption":"Confidence outputs from the classifier can be used as natural confidence measures for trading decisions.","type":"model","stated":"explicit","quote":"we introduce confidence-guided prediction and trading that leverages classification-based probability outputs as natural confidence measures and incorporates specialized regularization loss to enhance prediction reliability and guide trading decisions."}]},"datasets":{"status":"available","items":[],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"We use the public end-of-day trading dataset col-lected by Yahoo Finance1.","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":"USA stock market index","asset_class":"equities","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"unclear","headline_net_of_costs":false,"detail":null,"quote":null,"source":"conflict","rule":"R4b","candidates":{"front_matter":"partial","evidence_card":"yes","evidence_card_quoted":true},"conflict_kind":"graded","card_detail":"0.1% per trade","card_quote":"We consider a transaction cost of 0.1% for each trade.","meaning":"the platform classifier and the paper-text extraction disagree, so no value is asserted"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Binary encoding with feature fusion (BN+FS) achieves the highest annualized return of 8.6% and ICLR of 0.450 on the US stock market.","kind":"performance","quote":"BN+FS achieving the highest annualized return of 8.6% and ICLR of 0.450."},{"finding":"Adding mean confidence (BF+Mean) raises MLP’s ICLR from 0.284 to 0.367 and LSTM’s Sharpe Ratio from 0.560 to 0.733.","kind":"predictive-accuracy","quote":"Adding mean confidence (BF+Mean) improves performance significantly, with MLP’s ICLR increasing from 0.284 to 0.367 and LSTM’s SR from 0.560 to 0.733."},{"finding":"Combining confidence mechanisms with decision making (BF+Trend+DM) yields the highest Sharpe Ratio of 1.324 for MLP, up from 0.916.","kind":"performance","quote":"BF+Trend+DM achieves the highest SR of 1.324 with MLP, up from 0.916."},{"finding":"Binary encoding improves direction prediction, with IC for Transformer models increasing from 0.021 to 0.029 and ICLR from 0.234 to 0.310.","kind":"predictive-accuracy","quote":"For Transformer models, BN enhances IC from 0.021 to 0.029 and ICLR from 0.234 to 0.310."},{"finding":"Fusion in latent space and binary encoding together boost model performance across architectures, e.g., MLP IC from 0.018 to 0.024 and Sharpe ratio from 0.584 to 0.855.","kind":"performance","quote":"For MLP, introducing BN improves the IC from 0.018 to 0.024 and the Sharpe ratio from 0.584 to 0.855."}],"reported_performance":{"strategy":"CUBIC","sharpe":0.916,"sharpe_benchmark":null,"annual_return_pct":9.2,"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":36,"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":"2026-11-14T17:38:06Z"},"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/"}