Abstract: This document describes a data processing system for processing a feature vector that comprises features (one or more) that are indicative of dyslexic behavior that are indicative of dyslexic behavior. The data processing system includes a feature classification engine that generates classification metrics for a feature vector. Machine learning logic is used to determine a classification metric for each feature. Features that have a classification metric below a pre-determined threshold are removed. The data processing system includes a prediction engine that generates a prediction value indicative of a predicted likelihood of dyslexia. The prediction engine assigns, to each remaining feature, based on the classification metric of the respective remaining feature, a prediction weight and determines the prediction value based on the prediction weights.

Abstract: This document describes a data processing system for processing a feature vector that comprises features (one or more) that are indicative of dyslexic behavior that are indicative of dyslexic behavior. The data processing system includes a feature classification engine that generates classification metrics for a feature vector. Machine learning logic is used to determine a classification metric for each feature. Features that have a classification metric below a pre-determined threshold are removed. The data processing system includes a prediction engine that generates a prediction value indicative of a predicted likelihood of dyslexia. The prediction engine assigns, to each remaining feature, based on the classification metric of the respective remaining feature, a prediction weight and determines the prediction value based on the prediction weights.

Abstract: This document describes a data processing system for processing a feature vector that comprises features (one or more) that are indicative of dyslexic behavior that are indicative of dyslexic behavior. The data processing system includes a feature classification engine that generates classification metrics for a feature vector. Machine learning logic is used to determine a classification metric for each feature. Features that have a classification metric below a pre-determined threshold are removed. The data processing system includes a prediction engine that generates a prediction value indicative of a predicted likelihood of dyslexia. The prediction engine assigns, to each remaining feature, based on the classification metric of the respective remaining feature, a prediction weight and determines the prediction value based on the prediction weights.