Aito represents a fundamental shift in machine learning implementation. Instead of training models, it calculates statistics on-demand, enabling real-time predictions without the traditional ML pipeline.
Traditional ML trains fixed models on historical data. Aito calculates probabilities dynamically using Bayes' theorem, enabling more flexible and explainable predictions.
Predictions are calculated from raw statistics, not trained models
P(Y|X) calculated directly using indexed conditional probabilities
Bayesian networks discover relationships without manual feature engineering
Mutual information metrics identify predictive relationships
Every prediction includes confidence scores for automation decisions
Posterior probabilities provide calibrated uncertainty estimates
Aito implements sophisticated Bayesian inference through specialized database indexes
P(Y|X) = P(X|Y) × P(Y) / P(X)
The key innovation: specialized indexes that make statistical calculations as fast as database queries
Similar to search engines, but using indexes optimized for statistical operations
Word 'invoice' → items {id1, id2, id3} with counts
Database contains indexes, caches and precomputation designed for fast inference
Precomputed indexes and offsets over links, row feature vectors
Inference uses database primitives directly and maintains low-level caches
Inference operates directly on indexes and maintains specialized segment-level caches
Aito provides specialized inference methods optimized for different prediction scenarios
Direct Bayesian inference for single-target predictions
{ "from": "invoices", "where": { "vendor": "Acme Corp" }, "predict": "category" }
Find items that maximize a goal probability
{ "from": "impressions", "where": { "user": "alice" }, "recommend": "product", "goal": { "purchased": true } }
Flexible statistical queries for complex scenarios
{ "from": "impressions", "where": { "user": "alice", "product.name": { "$match": "milk" } }, "get": "products", "orderBy": { "$multiply": [ { "$similarity": { "name": "milk" } }, { "$p": { "$context": { "click": true } } } ] } }
Aito's representation learning automatically discovers high-level concepts from raw data, eliminating the need for manual feature engineering
Traditional ML requires explicit feature engineering - manually creating features like 'is_weekend' or 'high_value_customer'. Aito automatically discovers these patterns through representation learning based on minimum description length (MDL) principles.
Identifies co-occurring features that form meaningful concepts
Walking like a duck + Swimming like a duck + Quacking like a duck → Concept: "duck"
Combines low-level features into high-level representations
{ "$and": [ { "$has": "rent" }, { "$has": "real" }, { "$has": "estate" } ] } → Concept: "real estate rental"
Recognizes entities and relationships without explicit configuration
"Invoice to Johnson in IT department" → Automatically matches to employee records and department patterns
How Aito uses word matching and Bayesian priors for robust predictions
Uses metadata to assign initial probabilities to prediction targets
Technique: Bayesian priors based on prediction target metadata
If customer prefers bread, increase purchase probability for items with bread property
Automatically leverages word and feature matches in inference
Technique: Bayesian priors based on cross-field matching statistics
If description field contains 'Sarah', assume correct processor is Sarah, even if this exact combination hasn't been seen before
Leverages known metadata to inform predictions about new features
Technique: Bayesian priors based on metadata similarity
If user has vegetarian metadata tag, infer vegetarian preferences based on similar users
Bayesian priors prevent overfitting and handle sparse data
Approach: Uses category distribution of similar vendors as prior
Benefit: Reasonable predictions even with zero examples
Approach: Balances specific evidence with general patterns
Benefit: Avoids overfitting to anomalies
Approach: Continuous prior updating as data accumulates
Benefit: Adapts to drift without retraining
Powerful operators that enable custom feature engineering at query time
Focus predictions on specific data subsets
{ "from": "invoices", "where": { "region": "EU", "$on": [ { "amount": { "$gt": 10000 } }, { "region": "EU" } ] }, "predict": "approval_time" }
Use case: Segment-specific predictions without separate models
Find similar items using weighted feature similarity
{ "from": "products", "where": { "$knn": { "k": 10, "near": { "name": "Acme CRM", "category": "software" } } } }
Use case: Similarity-based recommendations and matching
Automatic discretization of continuous variables
{ "from": "customers", "where": { "age": { "$numeric": 25 } }, "predict": "churn_risk" }
Use case: Handle numeric features without manual binning
{ "from": "transactions", "where": { "$on": [ { "$knn": { "k": 5, "near": { "description": "AWS Consulting" } }, "amount": { "$numeric": { "$gte": 1000 } } } }, { "region": "EU" } ] }, "predict": "fraud_risk" }
Build sophisticated feature engineering logic without code
Rigorous testing demonstrates Aito's performance compared to traditional ML approaches
UCI Machine Learning Repository benchmark results
Dataset | Aito | Random Forest | SVM | Insight |
---|---|---|---|---|
Spam Detection | 95% | 97% | 87% | Competitive with ensemble methods |
Shuttle | 98% | 99% | 78% | Excellent on multi-class problems |
Letter Recognition | 88% | 91% | 82% | Strong pattern recognition |
Adult Income | 82% | 85% | 79% | Handles mixed data types well |
Aito achieves 96% mean accuracy across standard benchmarks, ranking 3rd out of 8 methods tested
20-200ms
vs hours/days for model training
90-98% typical
vs 92-99% for specialized models
Automatic
vs weeks of manual work
Zero
vs continuous retraining
Purchase invoice automation
Product catalogue matching (IKEA to Helsingö)
Purchase invoice processing
Explore different query types with our interactive widget
Explore different query types with our interactive widget
Classify with calibrated confidence scores
{ "from": "invoices", "where": { "Description": "Aws Cloud" }, "predict": "Processor", "select": [ "$p", "Name", "Department", "Role" ] }
Episto Oy
Putouskuja 6 a 2
01600 Vantaa
Finland
VAT ID FI34337429