Prediction of Individual Learning Experience in Terms of “Number Of Steps” as Solution Components of Arithmetic Tasks

Abstract

The paper is devoted to the study of learning in solving arithmetic problems in the conditions of digital learning. Learning is considered as a functional system, the level of differentiation of which can be related to the number of steps in problem solving. The goal of the paper is to find out the model that could more accurately describe the relationships between the number of steps and task types on Addition data and predict the number of steps on Multiplication data. The hypothesis is that with a given similarity, there is a correlation between the number of steps in solution of addition and multiplication tasks. We have created two experimental courses, “Addition” and “Multiplication” to make participants learn optimal methods of calculation of arithmetic tasks. The courses have the same structure and belong to a common domain (arithmetic tasks). It is a condition for similarity of learning. We have found out significant positive correlation between the number of steps in solution of addition and multiplication tasks on average for the sample. We have used a regression-based classification. Few models have been built for each individual personally and trained on the Addition data, then applied on the Multiplication data. The best of these models correctly predict the number of steps in 33–40% of tasks (SD = 17–22%, max = 88%), in other tasks they give a prediction with a small error of 1–2 units, which indicates its medium predictive ability.