SELECT algorithm and open-source trial dataset

Product or Programme · All products and programmes
Evidence · 4 claims (3 for, 1 mixed) · 1 study (1 causal), q2 · 0 of 1 report an effect size · 4 claims rest on one study

Description

An open-source release by Upadhyay et al. containing the SELECT algorithm implementation and randomized-trial learning data for studying machine-learning-based instruction sequencing and memorization.

Components

• SELECT algorithm and open-source trial dataset released for research at the intersection of cognitive science and machine learning: The authors released an open-source implementation of their algorithm and all data gathered during the randomized controlled trial, "to facilitate research at the intersection of cognitive science and machine learning". The data and code are available at the GitHub repository Networks-Learning/spaced-selection. The trial data comprise more than ~16.75 million answers to ~1900 questions by ~50,700 learners in ~628,000 study sessions. (Utkarsh Upadhyay et al. (2021))

Claims

• The selection algorithm affects engagement: select and difficulty groups were more likely to return within 4–7 days than the random group, but select-group learners were more likely to stop using the app in the initial 2 days [~M]
• ML-based question selection (SELECT) lowers learners' normalized empirical forgetting rate relative to difficulty-ordered and random selection after controlling for review time and number of reviews [+M]
• Algorithm-selected learners remember content over ~69% longer, with median half-life increases of ~92% vs random and ~40% vs difficulty groups [+M]
• Regression analysis shows the spacing effect holds in aggregate and the select group's advantage over other groups increases with number of reviews [+M]

Related Products and Programmes

-

Key Sources

• Utkarsh Upadhyay, Graham Lancashire, Christoph Moser and Manuel Gomez-Rodriguez. (2021). Large-scale randomized experiments reveals that machine learning-based instruction helps people memorize more effectively. npj Science of Learning 6:26. https://doi.org/10.1038/s41539-021-00105-8

Page metadata

Field	Value
type	product
id	select-algorithm-and-open-source-trial-dataset
title	SELECT algorithm and open-source trial dataset
description	An open-source release by Upadhyay et al.
status	review
product_kind	dataset
generated	by process:settle-candidates on 2026-10-26
trust	unverified — no one has confirmed this page's content

Frontmatter is the page's machine-readable record — see the Schema & Guide.