Tag: research-backtesting
Concepts
- Alert Fatigue and Escalation Policy
- Alternative Data Coverage Bias
- Alternative Data Diligence and Consent
- The Appraisal Ratio
- Arithmetic Versus Geometric Mean Returns
- Simulating Opening and Closing Auctions
- Audit Trail Requirements for Research
- Back-Adjusted Price Series
- Backtest PnL Attribution
- Start and End Date Sensitivity
- Bad Tick Filtering
- Bar Aggregation and Resampling Choices
- Benchmark-Relative Versus Absolute Evaluation
- Benchmark Selection for Backtests
- Blind Reimplementation from Spec
- Block Bootstrap of Return Series
- Break-Even Transaction Cost Analysis
- Brinson Performance Attribution
- Calibrating Alert Thresholds and False Alarm Rates
- Cancel-Ahead and Queue Decay Models
- Cancel-Replace Races in Simulation
- Cash Drag and Idle Balance Accounting
- Change Control for Live Strategies
- Class Imbalance in Financial Labels
- Commission and Fee Modeling
- Concept Drift in Financial Models
- Continuous Futures Contract Construction
- Corporate Actions Inside the Simulation Loop
- Cost-Adjusted Sharpe Ratio
- Crisis-Period Carve-Out Testing
- Cross-Market Replication Tests
- Crypto Market Data Pitfalls
- Building a Custom Benchmark
- Daily PnL Attribution in Production
- Data Versioning and Lineage
- Deep Generative Limit Order Book Simulators
- Delisting Returns
- Discrete-Event Scheduling in Backtest Engines
- Attributing a Drawdown to Positions
- Drawdown-Based De-Risking Triggers
- Effective Number of Independent Trials
- Perturbing Entry and Exit Rules
- Environment Pinning and Containerization
- Exchange Calendars and Trading Holidays
- Execution Timing Randomization
- Expanding Versus Rolling Training Windows
- Expected Versus Realised PnL Bands
- Controls on Expert Network Usage
- Feature Drift Detection in Production
- Feature Neutralization
- Feature Selection Bias
- Feature Stores for Research
- Fill Quality and Venue Scorecards
- Fundamental Data Report Lags
- Futures Roll and Expiry in Simulation
- FX Conversion in Multi-Currency Backtests
- GAN-Generated Market Scenarios
- Gross Versus Net-of-Cost Performance
- Grouped Cross-Validation for Panel Data
- Haircut Sharpe Ratio
- Heartbeats and Staleness Detection
- High-Water Marks and Fee Drag
- Historical Scenario Replay
- Hit Rate Versus Payoff Ratio
- Holdout Budget and Peek Accounting
- Holdout Set Contamination
- Incremental Value Over the Existing Book
- Independence of the Validation Function
- Index Membership History
- Information Barriers and Wall-Crossing
- Intraday Versus Daily Backtest Granularity
- Investment Committee Sign-Off
- Capturing Knowledge from Retired Strategies
- L1, L2 and L3 Data Fidelity for Simulation
- Label Horizon Selection
- Lo's Autocorrelation-Adjusted Sharpe
- Market Data Replay Versus Resimulation
- Mergers and Spinoffs in Price History
- Microprice-Based Fill Models
- What a Model Document Must Contain
- Model Governance and Model Risk
- Input Outlier Guards Before the Model
- Model Inventory and Risk Tiering
- Model Retraining Cadence
- Multi-Asset Simulation Architecture
- The Multi-Currency Cash Ledger in Simulation
- Multi-Venue Simulation and Routing
- Noise Injection Robustness Tests
- Order Book Reconstruction from Message Feeds
- Order Type Coverage in Simulators
- Paper, Pilot and Full-Size Validation Stages
- Parameter Sensitivity Analysis
- Parameter Stability Over Time
- Partial Fills and Order Splitting
- Personal Account Dealing Policy
- Point-in-Time Universe Construction
- Population Stability Index for Live Models
- Position and Cash Reconciliation Breaks
- Statistical Power Analysis for Backtests
- Pre-Registration of Research Hypotheses
- Price-Time Priority Matching Rules
- Simulating Pro-Rata Matching
- Random Seeds and Determinism
- Reconciliation Tolerances Between Implementations
- Red-Teaming a Strategy
- Regime-Stratified Validation
- Research Peer Review and Code Review
- The Research Diary
- Research Idea Intake and Triage
- Research-to-Production Handoff
- Researcher Degrees of Freedom
- Residual Quantity Handling After Partial Fills
- Restatements and Data Revisions
- Reverse Stress Testing a Strategy
- Comparing Strategies at Equal Risk
- Rolling Performance Windows and Stability
- Rolling Sharpe Alarm Thresholds
- Schema Drift and Field Definition Changes
- Security Master and Identifier Mapping
- Self-Trade Prevention in Simulation
- Sensitivity to Cost Assumptions
- Sensitivity to Rebalance Frequency
- Sensitivity to Universe Definition
- Shadow Trading and Paper Portfolios
- Short-Sale Restrictions and the Uptick Rule
- Simulating Acks, Rejects and Exchange Responses
- The Simulation Clock and Event Loop
- Spanning Tests for New Strategies
- SR 11-7 and Model Risk Management Guidance
- Stale Prices and Nonsynchronous Trading
- The Stationary Bootstrap
- Strategy Decommissioning Criteria
- Strategy Post-Mortem Analysis
- Structural Break Checks in Strategy Returns
- Surrogate Data Testing
- Synthetic Market Data for Backtesting
- Validating a Strategy on Synthetic Price Paths
- System Health Metrics for Trading Systems
- T-Statistic Hurdles for New Factors
- Tail Ratio and Gain-to-Pain Ratio
- The Lockbox Dataset
- Three Lines of Defence in a Quant Firm
- Tick-Driven Versus Bar-Driven Simulation
- Ticker Recycling and Symbol Collisions
- Timestamp Provenance: Exchange Versus Vendor
- Tracking Error Against the Backtest
- Trade-Level Versus Portfolio-Level Metrics
- Trading Halts and Limit Moves
- The Trading Incident Response Runbook
- Trend-Scanning Labels
- Turnover-Adjusted Alpha
- Unit Testing Quant Research Code
- Vendor Backfill and History Rewrites
- Vendor Licence and Data Usage Rights
- Vendor Reconciliation and Cross-Checks
- Vintage Databases and As-Of Joins
- Walk-Forward Efficiency Ratio
- Warmup and Burn-In Periods
- White's Reality Check
- Zero-Intelligence Trader Models