knew ton, platform

http://www.knewton.com/platform/

1. Data Collection

Enables Knewton to process and analyze the huge amounts of data produced by the learning applications that we power.

MODEL COMPUTATION ENGINE 
Processes data from real-time streams and parallel distributed cluster computations for use by the Inference and Personalization Infrastructures.

ADAPTIVE ONTOLOGY 
Maps the relationships between individual concepts that make up learning content, then integrates desired taxonomies, learning objectives, and student interactions.

2

Inference

Generates insight from collected data and allows Knewton to provide personalization features within learning apps

PSYCHOMETRICS ENGINE 
Evaluates student proficiencies, content parameters, instructional efficacy of content, assumptions about conceptual relationships, and more.

STRATEGY ENGINE 
Evaluates sensitivity of students to content presentation, assessment types, teaching strategies, pacing, and more.

FEEDBACK ENGINE 
Unifies inference data and feeds results back into the Adaptive Ontology, updating conceptual relationships automatically.

3. Personalization

Empowers teachers and students using Knewton- powered learning apps with real-time model-driven recommendations, actionable insights, and unified learning histories.

RECOMMENDATION ENGINE 
Prioritizes suggestions of what to do right now. Balances instructor- and student-determined goals, student strengths and weaknesses, student engagement, and more.

PREDICTIVE ANALYTICS ENGINE 
Provides detailed reports and metrics used by students, teachers, and parents. These predict the rate and likelihood of goal achievement, expected scores, proficiency, and more.

UNIFIED LEARNING HISTORY 
Enables each student to connect their learning experiences across disparate learning apps, subject areas, and time. Provides more seamless and comprehensive educational experiences in any Knewton-powered app.