Stock Pattern Assistant (SPA): A Deterministic and Explainable Framework for Structural Price Run Extraction and Event Correlation in Equity Markets

Understanding how prices evolve over time often requires peeling back the layers of market noise to identify clear, structural behavior. Many of the tools commonly used for this purpose technical indicators, chart heuristics, or even sophisticated predictive models leave important questions unanswered. Technical indicators depend on platform-specific rules, and predictive systems typically offer little in terms of explanation. In settings that demand transparency or auditability, this poses a significant challenge. We introduce the Stock Pattern Assistant (SPA), a deterministic framework designed to extract monotonic price runs, attach relevant public events through a symmetric correlation window, and generate explanations that are factual, historical, and guardrailed. SPA relies only on daily OHLCV data and a normalized event stream, making the pipeline straight-forward to audit and easy to reproduce. To illustrate SPA’s behavior in practice, we evaluate it across four equities-AAPL, NVDA, SCHW, and PGR-chosen to span a range of volatility regimes and sector characteristics. Although the evaluation period is modest, the results demonstrate how SPA consistently produces stable structural decompositions and contextual narratives. Ablation experiments further show how deterministic segmentation, event alignment, and constrained explanation each contribute to interpretability. SPA is not a forecasting system, nor is it intended to produce trading signals. Its value lies in offering a transparent, reproducible view of historical price structure that can complement analyst workflows, risk reviews, and broader explainable-AI pipelines.

💡 Research Summary

The paper introduces the Stock Pattern Assistant (SPA), a deterministic, explainable framework for dissecting equity price series into monotonic “runs” and linking those runs to public events. SPA requires only daily OHLCV data and a normalized stream of timestamped events (e.g., earnings releases, product launches). The pipeline consists of six modular stages: (1) data ingestion and validation, (2) preprocessing that converts prices to signed daily returns dₜ, (3) deterministic run detection that groups consecutive identical signs into maximal intervals Rₖ=