QuantifyAI Algorithm Statistics
Comprehensive Analysis of Systematic Equity Trading Strategy
This analysis presents the results of 6 long-term simulations conducted with Brainpower Trading’s QuantifyAI algorithm, each spaced 7 days apart to test temporal sensitivity and robustness.
1 Overview
Strategy Overview
This simulation showcases a systematic equity trading strategy using a scanner and model-based execution logic between 2018 and 2025, operating on daily intervals. The system continuously monitors 1,146 stocks and ranks them using a custom scoring algorithm based on technical signals. A maximum of 10 concurrent positions can be held at any time, each with a fixed capital allocation of $100,000 for each slot.
Each day, the scanner evaluates all stocks and scores them based on key technical indicators. If a stock’s score exceeds the predetermined allocation threshold, it is assigned to an available capital slot.
Between 2018 and 2025, these simulations illustrate the performance of a disciplined, algorithmic model-driven, and machine learning powered equity trading approach that operates on a daily cadence. The strategy employs a dynamic screening mechanism to evaluate a broad universe of equities, identifying high-conviction opportunities through a proprietary ranking framework. At any given time, the system maintains a concentrated portfolio, with capital allocated evenly across a limited number of positions. The result is a methodical, data-informed process designed to adapt to evolving market conditions while preserving consistency in execution.
The six trading simulations presented do not incorporate the application of the downside risk mitigation protocol. These simulations were designed to demonstrate the performance potential of the core long term strategy without any external capital preservation overlays. However, in all live trading environments, a strict downside protection mechanism will be applied to each position or portfolio allocation. This risk management layer is designed to limit losses in volatile market conditions, thereby enhancing capital preservation and improving the overall risk-adjusted returns during real-time execution.
Once a stock is allocated to a capital slot by the BPT scanner, a dedicated trading model begins monitoring its price action in real-time. This model evaluates buy and sell opportunities using a weighted combination of technical indicators, patterns and other proprietary assessment tools, acting only when the confidence of a signal exceeds a predefined threshold, ensuring trades are executed with a high degree of conviction.
The model operates with distinct sets of pre-optimized weights—one tailored for bullish market conditions, and the other for bearish or uncertain environments. These weights determine the influence each indicator has on the model’s decision-making process. Each indicator generates a directional output—Buy, Sell, or Hold—which is converted into a numerical value over a rolling time window.
Market conditions are continuously assessed using the proprietary BPT Indicator, which guides the model in selecting the appropriate scheme. A trade is only triggered—whether entering, shorting or exiting a position—when the score surpasses the predefined confidence threshold. This framework blends dynamic deterministic technical logic with adaptive, probabilistic weighting, enabling responsive, data-driven trading decisions in varying market environments
| Parameter | Value |
|---|---|
| Stock List | 1,146 stocks |
| Initial Cash per Slot | $100,000.00 |
| Number of Slots | 10 |
| Min Timedelta | 365 days |
| Interval | 1d (Daily) |
| Period | 365d |
| Selected Time Frame | Long Term Strategy |
| Trading Strategy | QuantifyAI Model |
Simulation Timeline & Performance Summary
The analysis includes 6 long-term simulations conducted with the following start dates, each spaced 7-10 days apart:
| Simulation | Start Date | End Date | Duration | Cumulative Return | CAGR | Sharpe | Sortino | Volatility (Ann.) | View Report | View Trades |
|---|---|---|---|---|---|---|---|---|---|---|
| 2018-01-01 to 2025-01-01 | 2018-01-01 | 2025-01-01 | 7 years | 479.14% | 19.97% | 0.57 | 1.16 | 53.41% | View Report | View Trades |
| 2018-01-07 to 2025-01-07 | 2018-01-07 | 2025-01-07 | 7 years | 785.75% | 25.3% | 0.73 | 1.33 | 42.37% | View Report | View Trades |
| 2018-01-14 to 2025-01-14 | 2018-01-14 | 2025-01-14 | 7 years | 152.79% | 10.13% | 0.33 | 18.56 | 2619.75% | View Report | View Trades |
| 2018-01-21 to 2025-01-21 | 2018-01-21 | 2025-01-21 | 7 years | 438.06% | 19.07% | 0.68 | 1.08 | 34.27% | View Report | View Trades |
| 2018-02-01 to 2025-02-01 | 2018-02-01 | 2025-02-01 | 7 years | 169.86% | 10.46% | 0.4 | 87.64 | 11351.02% | View Report | View Trades |
| 2018-02-07 to 2025-02-07 | 2018-02-07 | 2025-02-07 | 7 years | 306.8% | 15.06% | 0.43 | 1.21 | 90.78% | View Report | View Trades |
1.0.1 Portfolio Performance Summary
| Metric | Average | Minimum | Maximum | Standard Deviation |
|---|---|---|---|---|
| Cumulative Return | 388.73% | 152.79% | 785.75% | 236.02% |
| CAGR | 16.67% | 10.13% | 25.30% | 5.92% |
| Sharpe Ratio | 0.52 | 0.33 | 0.73 | 0.16 |
| Sortino | 18.50 | 1.08 | 87.64 | 34.58 |
| Volatility (Ann.) | 2365.27% | 34.27% | 11351.02% | 4520.09% |
2 Co-Founders
Vincent Brown
Co-founder & CEO
LinkedIn Profile
Anthony Denaro
Co-founder & CIO
LinkedIn Profile
Seng Yew
Co-founder & CIO