Trading Literacy

Accepts natural language questions about trading activity and portfolio performance, processing them through an LLM-based conversational interface that interprets trader intent and generates contextual responses. The system maintains conversation state across multiple turns, allowing follow-up questions and drill-downs into specific trades or time periods without requiring users to re-upload or re-specify their data context. This differs from traditional dashboard analytics by treating the portfolio as a conversational subject rather than a static visualization.

Analyzes sequences of trades to identify recurring behavioral patterns — such as revenge trading after losses, overtrading in specific market conditions, or systematic bias toward certain asset classes. The system likely uses statistical aggregation and LLM-based narrative synthesis to surface patterns that would require manual review across hundreds of trades. This capability bridges quantitative metrics (win rate, drawdown) with qualitative behavioral insights (emotional decision-making, discipline lapses).

Accepts trading data uploads in multiple formats (CSV, JSON, broker statements) and normalizes them into a standardized internal schema for analysis. The system likely performs format detection, field mapping, and data validation to handle variations in how different brokers export trade records. This is a critical integration point that avoids the friction of direct broker API connections but requires users to manually export and upload their data.

Computes standard trading performance metrics (win rate, profit factor, Sharpe ratio, maximum drawdown, average trade duration) from uploaded trade data and contextualizes them through conversational explanation. Rather than displaying raw numbers, the system explains what each metric means, how the trader's performance compares to benchmarks, and what the metrics reveal about trading style. This bridges the gap between quantitative rigor and accessibility for non-technical traders.

Enables users to ask questions about specific individual trades or trade sequences, receiving detailed analysis of entry/exit decisions, timing, position sizing, and outcomes. The system retrieves relevant trade data from the portfolio context and generates explanations of what happened, why it happened, and what could have been done differently. This capability supports iterative learning by allowing traders to drill down from high-level patterns to specific trade decisions.

Allows users to ask questions that implicitly or explicitly filter trades by time period, market condition, or asset class (e.g., 'How did I trade during the March 2023 rally?' or 'Compare my performance in bull vs. bear markets'). The system interprets these natural language filters, applies them to the portfolio data, and generates comparative analysis. This capability enables traders to understand how their behavior and performance vary across different market regimes without requiring manual data slicing.

Analyzes position sizing decisions across the portfolio and identifies patterns in risk management — such as oversized positions, inconsistent stop-loss placement, or risk-per-trade variance. The system calculates metrics like risk-per-trade percentage, position size relative to account, and maximum exposure, then generates coaching feedback on whether sizing is appropriate for the trader's stated risk tolerance. This addresses a critical gap in trader education where position sizing discipline directly impacts long-term survival.

Maintains conversation state and portfolio context across multiple user sessions, allowing traders to return to previous analyses and continue drilling down into patterns without re-uploading data or re-specifying context. The system stores conversation history, portfolio snapshots, and analysis state in a user-specific knowledge base, enabling continuity and reference to previous insights. This differs from stateless chatbots by treating the portfolio as persistent context that accumulates insights over time.

Generates educational explanations of trading principles, risk management concepts, and behavioral finance insights based on the trader's specific portfolio and performance data. Rather than generic trading education, the system contextualizes lessons to the trader's actual trades and patterns, making principles concrete and relevant. This capability positions the tool as a coach that teaches through example rather than a signal generator that predicts market moves.