AI TRADING AGENT ANALYSIS - Defense PPA — AI Trading Agent

60-Minute Timeframe  |  183 Days Actual Performance  |  March 2025 – March 2026

Performance Summary

Overview

Tickeron's Defense PPA AI Trading Agent is an automated swing trading system focused exclusively on PPA — the Invesco Aerospace & Defense ETF. Designed with a 60-minute entry timeframe and daily timeframe exit signals, the robot balances intraday precision with longer-duration swing holding, allowing it to capture meaningful price moves in one of the most momentum-driven sectors of 2025–2026.

Across 183 days of live actual performance, the robot delivered a Total Net Profit of $17,558.26 on 50 closed trades, with 41 of those trades profitable — an 82% win rate that is exceptionally high by any standard. The Profit Factor of 4.79 means that for every dollar lost, the system generated $4.79 in gross profit. These are not backtested simulations; they reflect live market execution using real-time price data.

What Is PPA?

PPA (Invesco Aerospace & Defense ETF) tracks the SPADE® Defense Index, a benchmark composed of companies systematically important to defense, military, national/homeland security, and U.S. government space operations. The fund invests at least 90% of total assets in index constituents, providing concentrated exposure to defense contractors, aerospace manufacturers, and national security technology firms.

PPA's performance has been exceptional in the current geopolitical environment:

• 1-Week P/L: +1.32%
• 1-Month P/L: +4.78%
• 1-Quarter P/L: +14.19%
• 6-Month P/L: +18.31%
• 1-Year P/L: +18.31%

Global defense spending is surging. NATO nations are accelerating procurement to meet the 2% GDP target. The U.S. has allocated over $850 billion to defense in fiscal year 2025. Multi-year order backlogs at major defense contractors provide sustained earnings visibility, making PPA one of the strongest-performing sector ETFs in the current macro landscape.

Strategy Mechanics & Technical Architecture

The robot's architecture blends two distinct timeframes into a unified decision engine — high-frequency entry detection with patient, swing-level exits.

60-Minute Pattern Recognition

Entry signals are generated on the M60 chart using high-frequency pattern analysis. The system scans for statistical edge conditions — momentum shifts, volume confirmation, and price structure — before initiating a position. This intraday granularity allows the robot to enter positions at optimal levels rather than chasing moves on daily charts.

FLM-Based Trend Filtering

Tickeron's proprietary Financial Learning Models (FLMs) validate each potential entry against the prevailing daily trend. This dual-timeframe confirmation process dramatically reduces false signals. A 60-minute setup that conflicts with the broader daily trend is filtered out before execution — a key reason why the robot achieves an 82% win rate across live trades.

Smart Swing Trading Exits

Exit signals are confirmed on the daily timeframe, allowing winning positions to develop fully rather than being prematurely cut by intraday noise. With an average trade duration of 4 days and a maximum of 19 consecutive wins worth $9,711.44, the robot demonstrates consistent forward momentum across multiple trade sequences.

Risk and Position Management

The robot supports up to 50 open positions simultaneously while deploying $33,000 per trade — a meaningful allocation designed to generate material returns per position. Despite this exposure, maximum drawdown per trade stands at just $1,662.21, and absolute drawdown across the entire live period was only $3,416.14 — a small fraction of the $17,558.26 in profits generated.

Tickeron FLMs: The Technology Behind the Win Rate

Financial Learning Models (FLMs) are Tickeron's proprietary AI architecture built specifically for financial market analysis. Unlike static, rules-based algorithms that react to fixed conditions, FLMs are dynamic systems that continuously learn from market data and adapt to evolving conditions.

Where a conventional algorithm might fire on a single moving average crossover, an FLM evaluates hundreds of variables simultaneously — price action structure, volume dynamics, intermarket relationships, trend velocity — and assigns probabilistic weights to each in real time. The result is a higher-confidence trade signal with significantly fewer false entries.

In the Defense PPA robot, FLMs serve a critical dual role: validating intraday entry signals for alignment with the daily trend, and dynamically adjusting signal thresholds based on current volatility regimes. When conditions deteriorate, the system becomes more selective. When trends are clearly established, it captures opportunity more aggressively.

This reflects the broader vision of Tickeron's CEO, Sergei Savastiouk, Ph.D. — to make institutional-grade AI trading tools accessible to every retail investor, democratizing a technology landscape previously dominated by quantitative hedge funds and proprietary trading desks.

Streak Analysis

The robot's streak profile underscores its resilience. The average winning streak of 8 trades versus an average losing streak of just 2 trades demonstrates that the FLM-based filtering is highly effective at clustering gains and cutting loss exposure quickly before extended drawdown sequences can develop.

Market Context: Why Defense Is Outperforming

The Defense PPA robot is trading in a macro environment that is providing exceptional structural tailwinds. Several forces are converging to support continued outperformance in the aerospace and defense sector:

• NATO Spending Acceleration: Member nations are rapidly scaling defense budgets to meet the 2% of GDP target, driving procurement demand across weapons systems, logistics, cybersecurity, and intelligence platforms.
• U.S. Defense Authorization: The U.S. allocated over $850 billion to defense in fiscal year 2025, with bipartisan support for continued expansion.
• Order Backlogs: Major defense contractors are reporting multi-year order backlogs, providing strong revenue visibility and earnings predictability.
• Space and Cyber: Government investment in space operations and cybersecurity is expanding rapidly, opening new revenue streams for PPA constituents beyond traditional hardware.
• Reshoring and Supply Chain: Defense supply chain reshoring initiatives are generating domestic manufacturing investment, supporting industrial defense firms in the index.

Who Is This Robot For?

The Defense PPA AI Trading Agent is explicitly designed to be accessible to beginner traders while delivering performance metrics that satisfy experienced participants.

• Beginners: The robot handles all technical analysis, entry/exit timing, and position management autonomously. No prior trading knowledge is required to deploy it.
• Intermediate Traders: The dual-timeframe architecture and FLM-based filtering provide a transparent, learnable framework for traders looking to deepen their understanding of systematic strategies.
• Experienced Traders: The 82% win rate, 4.79 Profit Factor, and 5.14 Profit/Drawdown ratio make this a compelling addition to a diversified robot portfolio.

The robot's Medium volatility classification and balanced Profit/Drawdown scenario make it particularly suitable for traders who prioritize capital preservation alongside growth — not just maximum returns at any cost.

Risk Factors & Important Considerations

Before deploying capital with any AI trading robot, traders must understand the following risk categories:

• Sector Concentration Risk: PPA is a single-sector ETF focused exclusively on aerospace and defense. A sudden policy shift — such as unexpected diplomatic de-escalation or a defense budget cut — could impact the entire position simultaneously.
• Market Regime Risk: The robot is calibrated for medium volatility environments. Sudden VIX spikes, black swan events, or flash crashes can cause even well-calibrated systems to generate rapid drawdowns.
• Geopolitical Reversal Risk: Much of PPA's current momentum is tied to elevated global defense spending. A material change in geopolitical conditions could rapidly reverse these tailwinds.
• Model and Execution Risk: AI models — including FLMs — learn from historical data patterns that may not repeat. Platform outages, data feed interruptions, or execution delays can affect live performance.
• Capital Risk: No trading system eliminates the possibility of extended losing streaks. Traders should only allocate capital they can afford to lose entirely.

DISCLAIMER

The information in this document is provided for general informational and educational purposes only and is not intended as investment advice, a recommendation to purchase or sell any security, or an offer or solicitation related to investments. It does not consider your personal financial situation, goals, or risk profile. All investing carries inherent risks, including the possibility of losing your entire investment. Past performance does not assure future results. Always do your own research or consult a licensed advisor. Prices can go down as well as up. For full details, please review Tickeron's complete Disclaimers and Limitations at tickeron.com/app/legal.

Simulated Performance: All simulated performance results are derived solely from real-time calculations using historical data. Actual Performance results are derived from real-time calculations using current data. Net performance results deduct fees to provide a more accurate representation of returns experienced by the user.

Tickeron AI Perspective

 Disclaimers and Limitations

Contributor

Serhii Bondarenko|Expert

Serhii Bondarenko is an AI-focused trading strategist and financial markets analyst specializing in the development and application of AI trading bots and autonomous trading agents. His work combines technical analysis, fundamental analysis, and quantitative research to identify market patterns, forecast price movements, and analyze liquidity, volatility, and correlations across global stock markets. Serhii actively publishes market insights, forecasts, and trading frameworks on platforms such as Investing.com and Finextra, with a strong focus on AI-driven decision-making and next-generation algorithmic trading. His research aims to bridge the gap between traditional trading methodologies and advanced artificial intelligence, helping traders and investors navigate complex and rapidly evolving market conditions.

Notable companies

Industry description

Market Cap

High and low price notable news

Volume