Oak Fundix dashboard interface displaying predictive data models and risk indicators

Optimize Supplemental Income with Backtested AI Decision Models

Oak Fundix analyzes historical and real-time market data to generate risk-adjusted recommendations for gig economy professionals building income outside standard employment. Every model is validated against multiple market cycles before deployment.

Start Analysis View Historical Performance

The dashboard displays projected return ranges, model confidence intervals, and a risk score for each recommendation, updated as new data is processed.

Problem & Approach

Manual Analysis Does Not Scale with Irregular Work Hours

Gig economy income varies by week and by platform. Reviewing market data manually between shifts leaves limited time for structured decisions.

Where manual tracking falls short

  • Spreadsheet-based tracking cannot process new data fast enough to react to short-term price movement.
  • Irregular working hours limit the time available for research between shifts or gigs.
  • Single-source analysis overlooks correlations across asset classes and macro indicators.
  • Emotional decision-making increases exposure during volatile sessions.

How Oak Fundix processes the same data differently

Oak Fundix ingests market data continuously and applies predictive models trained on historical cycles. Recommendations are generated within defined risk parameters and delivered before manual review would be possible.

Decision latency comparison

Manual review
Spreadsheet model
Oak Fundix model

Illustrative comparison of time from data availability to a documented decision, based on internal process timing.

Platform Structure

Three Components Work Together on Every Recommendation

Each recommendation is the output of a predictive model, a risk constraint, and an execution window, applied in sequence rather than in isolation.

01

Predictive Models

Statistical and machine-learning models are trained on historical price, volume, and macroeconomic data to estimate probable outcome ranges for a defined time horizon.

02

Risk Management

Each recommendation is filtered through position-sizing and exposure limits set according to a user-defined risk tolerance, capping downside before capital is allocated.

03

Real-Time Execution

Recommendations are time-stamped against live market data so that the conditions used for analysis match the conditions at the point of decision.

Data refresh
Continuous intraday
Model retraining
Scheduled, cycle-based
Hosting region
EU data centers
Risk controls
User-defined limits
Methodology

Models Are Tested Against Historical Data Before Deployment

Every model follows a fixed validation sequence. No model reaches live recommendations without passing each stage below.

  1. Data Collection

    Historical price, volume, and macroeconomic data are aggregated across multiple market cycles, including periods of high volatility.

  2. Model Training

    Predictive models are trained on a defined historical window, separated from the data used later for validation.

  3. Backtesting

    Each model is run against historical periods it has not seen during training to measure how recommendations would have performed.

  4. Risk Scoring

    Outputs are assigned a risk score based on volatility, drawdown, and correlation with existing recommended positions.

  5. Live Monitoring

    Deployed models are monitored continuously, with performance compared against their backtested projections.

Transparency Statement

Backtested results describe how a model would have performed on historical data; they do not guarantee future performance. Market conditions change, and past patterns may not repeat. Oak Fundix publishes the time period and data set used for each backtest alongside the model's current live status.

Applications

Three Scenarios Common to Supplemental Income Planning

The scenarios below reflect situations frequently reported by users balancing gig work with a secondary income strategy.

Scenario A

Responding to Short-Term Market Volatility

During periods of rapid price movement, Oak Fundix recalculates risk scores and position recommendations as new data arrives, giving users a documented basis for reducing or adjusting exposure rather than reacting on sentiment alone.

Scenario B

Building a Long-Term Supplemental Portfolio

For users allocating a fixed portion of gig income on a recurring basis, Oak Fundix applies longer-horizon models and periodic rebalancing recommendations aligned with a defined time frame rather than daily price swings.

Scenario C

Mitigating Risk from Irregular Income

Because gig income fluctuates by week, Oak Fundix applies exposure limits calibrated to available capital, helping to prevent a single position from representing a disproportionate share of supplemental funds.

About Oak Fundix

Built for Decision Support, Not Automatic Guarantees

Oak Fundix was developed to give individuals without a background in quantitative finance access to the same class of data analysis used by institutional research desks. The platform presents recommendations with their supporting data, so users retain control over every decision.

All models operate within the data protection standards expected in the German market, with infrastructure hosted inside the EU and processes aligned with GDPR requirements.

Learn About Our Process
Oak Fundix data analysis workspace used for model development and monitoring
Frequently Asked Questions

Common Questions on Access, Safety, and Control

Do I need trading or financial analysis experience to use Oak Fundix?

No prior trading experience is required. Recommendations include the underlying risk score and projected range in plain language, and users set their own risk tolerance before any model output is generated.

Where is my data stored, and does it meet German data protection requirements?

Data is processed and stored on infrastructure located within the EU, in line with GDPR. Account and financial data are encrypted both in transit and at rest.

Can I override or ignore a recommendation from the AI model?

Yes. Oak Fundix presents recommendations for review; execution decisions remain with the user at every step. No position is taken automatically without explicit confirmation.

What happens to recommendations during periods of extreme market volatility?

Risk scoring is recalculated more frequently during high-volatility periods, and position-size recommendations are reduced according to the predefined risk parameters set by the user.

How is a model's historical performance verified before release?

Each model passes a backtesting stage against historical data it was not trained on. The backtest period and data source are documented and made available alongside the model's live status.

Questions not covered here can be directed to our support team through the contact page. Response times are provided during business hours, Monday through Friday.

Review the Data Behind Each Recommendation Before You Decide

Create an account to view model performance, risk parameters, and backtested results relevant to your supplemental income goals.

Start Analysis
Account data is encrypted in transit and at rest and hosted within EU data centers, in alignment with GDPR requirements. No automatic trading occurs without explicit user confirmation.