How We Score 445K+ Products

Ultra Processed Food List exists to answer a simple question: how processed is the food you eat? We apply algorithmic scoring to every branded food product in the United States, transforming raw ingredient lists and nutrition facts into two actionable numbers: a Processing Score and a Nutrition Score.

Our database currently contains 445K+ unique products, deduplicated by barcode from nearly 2 million USDA records, spanning 13 consumer-friendly categories, from 25,234 brands. Every product receives both scores, calculated through a deterministic pipeline that treats each item identically regardless of brand, price, or marketing claims.

Transparency is central to our mission. This page explains what goes into our scores, what data sources we use, where the system has known limitations, and how we validate results.

Our scores are our opinion. We choose which inputs count and how much each one matters, so a score reflects our judgment about processing and nutrition. It is not a measurement, a safety rating or a government classification. This page describes the inputs and the limits. We keep the exact weights private.

Why two scores? Processing and nutrition measure fundamentally different things. A food can be heavily processed yet nutritionally dense, or minimally processed yet nutritionally poor. Collapsing both dimensions into a single number loses information consumers need.

Every score in our system traces back to publicly available data from the United States Department of Agriculture. We do not rely on proprietary datasets, manufacturer partnerships, or user submissions.

Primary Source

USDA FoodData Central. The Branded Food Products database is our primary source. Manufacturers and retailers submit detailed product information including complete ingredient lists, nutrition facts panels, UPC barcodes, brand names, and product categories.

1.9M+ branded product records

What We Have Access To

• Full ingredient lists (ordered by weight)
• Complete nutrition facts (calories, macros, vitamins, minerals)
• UPC/barcode identifiers
• Brand names and product descriptions
• Serving size information

Data Freshness

The USDA dataset receives continuous updates from manufacturers. We run our complete processing pipeline quarterly to incorporate new products, updated formulations, and corrected entries.

Between major updates, our database reflects a point-in-time snapshot. Because product formulations do change, always verify current ingredients on the physical label.

Data coverage note: 96% of products have complete macronutrient data (calories, protein, fat, carbohydrates). Vitamin and mineral data is available for a smaller subset. Image coverage stands at 23% through UPC-based matching. Products without ingredient data cannot receive a Processing Score and are excluded from scoring.

We deliberately separated processing measurement from nutrition measurement. Each score captures a distinct dimension of food quality, and the interplay between them reveals patterns that neither score could surface alone.

Processing Score (1-32+)

Lower is better.

Measures how far a food has been transformed from its natural state through industrial processing. Based on ingredient count, the presence of artificial additives, preservatives, and manufacturing indicators.

Key inputs: ingredient count, artificial ingredients, HFCS, preservatives, hydrogenated oils, modified starches, chemical additives

Nutrition Score (0-10)

Higher is better.

Evaluates the nutritional profile based on the presence of nutrients the score rewards and the absence of those it penalizes. Starts at a baseline and adjusts based on positive and negative factors.

Key inputs: protein, fiber, added sugars, sodium, saturated fat, trans fat, fermented dairy content

The two scores are calculated independently, and they read different parts of the label:

• Processing Score reads the ingredient list alone: how many ingredients a product declares, and which of them belong to the classes of industrial ingredient named above.
• Nutrition Score reads the Nutrition Facts panel alone: protein, fiber, added sugars, sodium, saturated fat, trans fat and cholesterol. Nothing else enters it.

A product receives BOTH scores. They are never combined into one number.

Both are ranking instruments. A single score in isolation says less than the same score set beside the rest of the catalog, which averages 6.5 on processing and 4.40 on nutrition.

For detailed breakdowns of each scoring system, see our Processing Score Guide and Nutrition Score Guide.

The Processing Score measures the ingredient list and nothing else. It reads how many ingredients a product declares, and how many of those ingredients fall into the classes of industrial ingredient below. More of either ranks a product higher on the scale. The typical product in our catalog declares 15.2 ingredients and scores 6.5.

What Increases the Score

• Higher ingredient counts: A product declaring more ingredients ranks above one declaring fewer. A single-ingredient food sits near the bottom of the scale; a long industrial formulation sits near the top.
• Artificial ingredients: Artificial colors, flavors, and sweeteners that cannot be replicated in a home kitchen.
• High fructose corn syrup: An industrially produced sweetener requiring enzymatic conversion of corn starch.
• Hydrogenated oils: Industrial hydrogenation that creates trans fats and extends shelf life.
• Synthetic preservatives: BHA/BHT, sodium benzoate, potassium sorbate, and similar shelf-life extenders.
• Modified ingredients: Modified starches, protein isolates, and chemically altered food components.

Four Processing Levels

Final Processing Scores are mapped to four levels that provide plain-language context:

• Level 1, Minimally Processed: 20.9% of scored products
• Level 2, Processed: 27.3% of scored products
• Level 3, Highly Processed: 24.0% of scored products
• Level 4, Ultra-Processed: 27.8% of scored products

For a more detailed explanation of the Processing Score with real product examples, see our Processing Score Guide.

The Nutrition Score evaluates what a food provides nutritionally, independent of how it was manufactured. Scores range from 0 to 10, with higher scores indicating more nutritional value. The database average is 4.40.

Positive Factors (Increase Score)

• Protein content: Higher protein per serving increases the score
• Fiber content: Dietary fiber contributes positively
• Fermented dairy: Yogurt, kefir, and similar products receive a small bonus

Negative Factors (Decrease Score)

• Added sugars: The largest negative factor
• Sodium: Excess sodium reduces the score
• Saturated fat: High saturated fat content is penalized
• Trans fat: Any trans fat presence reduces the score

For a complete explanation, see our Nutrition Score Guide.

The NOVA food classification system is the most widely cited academic framework for categorizing food by processing level. Our system was informed by NOVA principles but designed to address specific limitations of categorical classification.

Where the Systems Agree

• Single-ingredient whole foods consistently receive the lowest processing classifications in both systems
• Products with artificial additives, HFCS, and hydrogenated oils are flagged as highly processed by both systems
• The same ingredient markers (emulsifiers, protein isolates, artificial sweeteners) drive classification in both frameworks

Where They Differ

• NOVA treats all ultra-processed foods equally; our system distinguishes a PS of 8.5 from a PS of 25.0
• NOVA does not account for nutritional content; we provide a separate Nutrition Score for that dimension
• NOVA classification requires expert judgment for edge cases; our algorithm applies the same rules to every product deterministically

Our position: NOVA is a valuable research framework and our system is complementary to it, not a replacement. We use a continuous score because consumers benefit from knowing that one Level 4 product can be several times more processed than another, even though both fall into NOVA Group 4. For a full explanation of NOVA, see our NOVA Food Classification Guide.

No scoring system is perfect. We believe transparency about limitations is more valuable than projecting false precision. Here are the known areas where our methodology has weaknesses or produces counterintuitive results.

Products That Score Unexpectedly High

Fortified health foods

Protein powders, meal replacement shakes, and fortified cereals often contain protein isolates, emulsifiers, and synthetic vitamins that trigger processing penalties, even though these products are marketed as healthy. The Nutrition Score helps balance this by reflecting actual nutrient content.

Products with long but simple ingredient lists

A trail mix listing fifteen nuts, seeds and dried fruits ranks above a product listing five, even though every one of those ingredients is minimally processed on its own. Ingredient count is a proxy for complexity, and an imperfect one.

Products That Score Unexpectedly Low

Simple but nutritionally poor foods

A candy made from sugar, corn syrup and food coloring scores lower on processing than a whole-grain bread listing a dozen identifiable ingredients. A short list ranks low whether or not the product provides anything nutritionally.

Incomplete ingredient data

Some products in the USDA database have abbreviated or incomplete ingredient lists. When ingredients are missing from the data, our algorithm cannot detect processing markers it cannot see. These products may receive artificially low scores.

Known Data Gaps

Categories that are harder to classify: Supplements, baby food, and ethnic/specialty foods present particular challenges. Supplements often contain dozens of synthetic vitamins and minerals that inflate processing scores even when the base product is simple. Baby food formulations vary widely. Ethnic and specialty foods may use traditional ingredients that our detection algorithm does not yet recognize as processing markers (or incorrectly flags as such). We continue to refine these categories with each pipeline update.

We run a multi-step incremental processing pipeline that takes raw USDA data and produces the scored product database you see on this site. Each stage validates its output independently, and the system is designed so that individual components can be updated without reprocessing the entire database.

Data Loading

Raw product data is loaded from USDA FoodData Central, including brand names, ingredient lists, nutrition facts, and UPC barcodes. Brand names are cleaned and categories are standardized.

Scoring & Analysis

Ingredient lists are parsed and analyzed for processing markers. Each product receives a Processing Score and Nutrition Score based on the criteria described above. Dietary attributes are computed from ingredient data.

Validation & Publishing

Every stage verifies data integrity before proceeding. Score distributions are checked against expected ranges and any anomalies are flagged for manual review before data reaches production.

Update schedule: We process major data refreshes quarterly to incorporate new products, updated formulations, and corrected entries from the USDA. Between major updates, we apply targeted corrections when significant data errors are identified. The production database is backed up separately and is never modified directly by the processing pipeline.

Scores are tools for comparison, not absolute judgments. They are most useful when comparing similar products within the same category or when evaluating the overall composition of your grocery basket.

Effective Uses

• Compare brands within a category: If you are choosing between three pasta sauces, search our database to find which has the lowest Processing Score
• Spot hidden processing: Two products may look similar on the front label, but their ingredient lists (and therefore their scores) can differ significantly
• Explore categories and brands: See which food categories and brands trend toward lower processing
• Read both scores together: two products can share a Processing Score and sit far apart on nutrition, which is the whole reason we publish both

What Scores Cannot Tell You

• Whether a food is "good" or "bad": Scores are descriptive, not prescriptive. Dietary context, individual health needs, portion sizes, and overall eating patterns matter enormously
• Real-time formulation changes: Manufacturers update recipes regularly. Our scores reflect the most recent USDA data, which may lag behind current labels
• Allergens: Some pages note allergens named in the ingredient list we have. Not finding one doesn't mean it's absent. Always read the package, and if your allergy is severe, don't rely on this site alone
• Health outcomes: We do not make health claims. Processing level correlates with certain dietary patterns but does not determine individual health outcomes

Our scoring system is informed by, but distinct from, several peer-reviewed frameworks for classifying food processing. We believe in transparency about our intellectual foundations.

The NOVA Framework

Monteiro et al. first proposed categorizing foods by processing extent in 2010^[1], later refined into the four-group NOVA system^[2] that has become the most widely used classification in nutrition research. The FAO adopted NOVA as a reference framework in 2017^[3]. Our Processing Score builds on NOVA's principles while providing a continuous scale rather than discrete categories.

Computational Approaches

Menichetti et al. (2023) demonstrated that machine learning can predict food processing levels from ingredient lists with high accuracy^[4], validating the approach of using ingredient-based signals, the same foundation our scoring algorithm relies on.

Methodological Critiques

Gibney et al. (2019) raised important methodological considerations about ultra-processed food classification systems^[5], including the heterogeneity within processing categories. Our two-score approach (separating processing from nutrition) directly addresses this concern by acknowledging that processing level alone does not determine nutritional value.

Frequently Asked Questions