预测极值、无利可图的策略：基于蜡烛图的币安现货时机模型的人工智能辅助审计
Predictive Extrema, Unprofitable Policies: An AI-Assisted Audit of Candle-Based Binance Spot Timing Models
浏览论文内容
中文总结 AI 辅助
研究基于蜡烛图的机器学习模型能否将加密货币极值预测转化为币安现货正向策略，通过模型运行和模拟器获取数值结果，经人工监督的AI代理辅助审计，结果显示多数测试协议未确立正向可执行策略价值，操作决策应为不交易。
中文摘要 AI 辅助
我们审计基于蜡烛图的机器学习模型在考虑成本后能否将加密货币极值预测或短期结果转化为币安现货的正向纸面策略。数值结果来自脚本化固定种子模型运行和确定性模拟器；人工监督的人工智能代理通过文献检索、单独任务批判、工件核对、文档记录和源打包支持7月20日的证据完整性修订，而非交易决策。在广泛的前期搜索条件下，后期最强证据为负面：在假设31个基点的完整周期成本下，一个不变的十对强制每日选择器在19个7月周期内损失了6.72%，有3次盈利和16次亏损。在7月特定模型的简短评估中，验证选择的局部最小值策略回报率为-1.79%，而局部最大值卖出套现/重新入场策略比持续持有表现差2.80%；它们11.11和12.21个基点的总平均优势甚至低于21个基点的压力。一个受古尔古尔启发、仅使用OHLCV的每日适应性模型获得了最低/最高ROC AUC为0.874/0.896，但平均精度仅为0.134/0.116，在七个周期内损失了44.30%，而买入并持有为-41.20%。一项法医审计还下调了早期的One4All“30天保留期”：其日期影响了先前的架构工作，其四小时结果范围在分割边界未清除，使用相同收盘价入场，且缺少原始结果目录。在所有测试的、大多为探索性的协议中，事件排名性能未确立正向可执行策略价值。每个操作决策仍为不交易。
英文摘要
We audit whether candle-based machine-learning models can turn predictions of cryptocurrency extrema or short-horizon outcomes into positive Binance Spot paper policies after assumed costs. Numerical results come from scripted fixed-seed model runs and deterministic simulators; human-supervised AI agents supported the July 20 evidence-integrity revision through literature retrieval, separately tasked critique, artifact reconciliation, documentation, and source packaging, not trading decisions. The strongest later-period evidence, conditional on extensive predecessor search, is negative: an unchanged ten-pair mandatory-daily selector lost 6.72\% over 19 July cycles at an assumed 31-bps completed-cycle cost, with 3 wins and 16 losses. In short model-specific July evaluations, the validation-selected local-minimum policy returned -1.79\%, while the local-maximum sell-to-cash/re-entry policy underperformed continuous holding by 2.80\%; their gross mean advantages of 11.11 and 12.21 bps were below even the 21-bps stress. A Gurgul-inspired, OHLCV-only daily adaptation attained minimum/maximum ROC AUC of 0.874/0.896 but average precision of only 0.134/0.116 and lost 44.30\% over seven cycles, versus -41.20\% for buy-and-hold. A forensic audit also downgraded an earlier One4All "30-day holdout": its dates had influenced prior architecture work, its four-hour outcome horizon was not purged at split boundaries, it used same-close entry, and its raw result directories were absent. Across the tested, mostly exploratory protocols, event-ranking performance did not establish positive executable policy value. Every operational decision remains NO\_TRADE.
发表机构
- Abdelmalek Essaâdi University（阿卜杜勒马莱克·埃萨阿迪大学）
机构由 AI 辅助整理，请以论文原文为准。
