How Eatomate Works

Receipt printers create predictable errors. We use research-backed confusion matrices that understand certain character pairs are commonly confused by OCR. This includes both single-character substitutions and multi-character segmentation errors where two characters are misread as one (or vice versa). Each confusion has a likelihood score.

Instead of treating all typos equally (standard Levenshtein distance), we weight matches by how likely the OCR error is. A common confusion costs less than a rare one, leading to better matches on real-world receipt data.

When you map a receipt item to a barcode once, the system remembers it with a confidence score. Repeated mappings increase confidence. The cache learns your shopping patterns at specific stores. By week 12, automated matching handles 99% of receipt items.

Your search text is matched against three databases (Barcode Database 2M+, Recipe Database 50K+, Alternative Names 100K+). If no exact match exists, Mistral AI generates a personalised recipe with full nutrition data, added to the database automatically.

Each food item has multiple aliases (e.g., "Shepherd's Pie" → ["Cottage Pie", "Mince and Potato Pie", "Meat and Tatties", ...]). Your search text is matched against ALL aliases in our 50K+ recipe database, ensuring you find the right item even with different naming conventions.

When no match is found (>80% confidence threshold), Mistral AI generates a complete recipe with:

• Ingredient list with quantities and classes
• Full nutrition profile per 100g
• Confidence scoring and usage tracking

When you finish an ingredient (milk carton empty), we use the equation: consumed = initial + purchased - waste - final. All quantities tracked in grams with uncertainty (e.g., 250g ± 15g). Gaussian error propagation combines uncertainties mathematically, locking historical meals at high accuracy.

Your real recipe differs from the database in many small, independent ways (different brands, oil amounts, cooking methods). CLT justifies modelling recipe-level error as Gaussian (~30% CV at 2σ per meal). Across a typical week's ~6-8 independent meal groups summing to 14,000 kcal, quadrature (root-sum-of-squares) reduces pre-reconciliation weekly error to ~18% at 2σ (~82% accuracy). Physics-based reconciliation then eliminates portion-size error and corrects recipe variance, achieving ~7% weekly error at 2σ (93% accuracy) by Week 4.

System learns your ingredient ratios automatically using weight (grams), not volume. Your bolognese might use 12g oil/100g while the generic database says 5g/100g. Reconciliation discovers this and updates recipe accuracy using exponential moving average with α=0.3 learning rate. Weight-based tracking eliminates density ambiguity (ml→g conversion errors).

All displayed values include 2 standard deviation (2σ) error bars, representing 95% confidence intervals. This means we're 95% confident the true value lies within the shown range. For example, "250g ± 15g" means we're 95% certain the actual portion was between 235g and 265g.

Unlike other apps that show false precision ("exactly 247.3 calories"), we show honest uncertainty ranges. Early weeks have wider error bars (±15-20%) which narrow over time (±7% by Week 4) as the system learns your specific patterns and recipes.

The doubly labeled water method — the gold standard for measuring free-living energy expenditure — has a precision of 2-8% CV (1σ), equivalent to ±4-16% at 2σ (Schoeller, 1988). Eatomate's reconciled weekly accuracy of ±7% at 2σ is comparable to or better than this laboratory standard — achieved passively, at home, with a £10 kitchen scale.