Stop measuring how close you were. Start measuring if you would have won.
Drop one or more CSVs with predictions & actual outcomes (6 columns maximum)
Works for stocks, sales, weather, sports-anything
No account required. Anonymous access includes 5 successful tool runs per rolling week.
File setup
Actuals stay visually dominant, the strongest forecast stays emphasized, and weaker candidates remain visible without taking over the chart.
Move from evaluation into advisory or execution.
Diagnose the dataset, select the target, assess dataset health, and get a structured model path before training.
Open Decision IntelligenceCarry forward the recommended shortlist, benchmark concrete candidates, and keep execution aligned with the upstream decision flow.
Open AutoMLThink of it like this: If you bet money on your predictions, would you make profit?
Being close isn't enough. Wrong direction can lose money.
Anyone who needs predictions that work, not just look good on paper.
This works for any prediction, not just finance
Scenario: You predict a stock at $101, it goes to $99.
Traditional: "Close! Only 2% error."
Quantsynth: "Wrong direction = you lost money."
Scenario: You predict 75°F, actual is 73°F.
Traditional: "Good job!"
Quantsynth: "Did people bring jackets? That's what matters."
Scenario: You predict a 10-point win, they win by 3.
Traditional: "Pretty close!"
Quantsynth: "You predicted a win and they won = profit."
Scenario: Predict $100K sales, actual is $80K.
Traditional: "20% error"
Quantsynth: "Did you overstaff? That costs real money."
Scenario: Model A: 95% accurate. Model B: 88% accurate.
Traditional: "Pick A"
Quantsynth: "Which one makes fewer expensive mistakes?"
Scenario: Predict price increase, it decreases 5%.
Traditional: "Small error"
Quantsynth: "Wrong direction = you bought at the peak."
Comparing what matters vs what gets measured
| WHAT MATTERS | TRADITIONAL APPROACH | QUANTSYNTH APPROACH |
|---|---|---|
| Getting Direction Right | Completely ignored (only cares about distance) | Primary focus (80% of success) |
| Actual Success Rate | No connection to outcomes | Directly measures if it works |
| When You're Wrong | Big mistakes kill your score | Understands asymmetric risk |
| Confidence Levels | Treats all predictions equally | Rewards being confident when right |
| Real-World Use | Great metrics, bad decisions | Optimizes for actual utility |
Not how close your predictions were, but how useful they actually are
FIS is QuantSynth's proprietary metric for evaluating forecast behavior from a decision-oriented perspective. It complements, but does not replace, conventional error metrics.
CER is QuantSynth's complementary proprietary metric for comparing forecasts from predictive and decision-oriented perspectives. It can rank candidates differently from FIS and conventional error metrics.
FIS and CER provide distinct proprietary comparison views. Use both alongside traditional errors, validation stability, baselines, and application-specific outcomes. Neither metric establishes deployment readiness on its own.
How traditional metrics get fooled by common prediction patterns
This model just predicts yesterday's price. It's incredibly common (moving averages, momentum strategies) and can look favorable on traditional metrics because it remains close to recent values. In a timing-sensitive task, it may react too late.
By the time you get the signal, the move already happened. You're always entering after the relevant event. This is a hypothetical timing failure, not a trading-performance result.
"Excellent fit!"
"Very accurate!"
"Weak under this hypothetical decision rule"
Hypothetical interpretation: delayed signals could be unfavorable after costs. Validate with realistic execution assumptions.
The transparency and privacy you need for sensitive data
Predictions processed in-memory. We evaluate your utility, we don't steal your alpha. No data storage, no tracking, no leaks.
Intended use, interpretation, evidence, and limitations are documented. The scoring mathematics and implementation remain proprietary.
Download reports include all the necessary data to complete your analysis. No black boxes.