Data analytics placement lifts college English completion at SUNY

The What Works Clearinghouse found that 34.30% of SUNY students placed by algorithms completed college-level English in their first semester, against 28.00%. Effects on degrees were uncertain.

  • 2 for a person

    In the first semester, 34.30% of students placed by the algorithms completed a college-level English course, against 28.00% of students placed by the standard procedure.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Reported benefit.
Evidence

foundstudiedreportedclaimed

Only the makers and the evaluators support the benefit.

Compared with

Students placed by the colleges' standard procedures, mostly ACCUPLACER cut points. Measured.

Without the system
28.00% completed a college-level English course in the first semester
With it
34.30%
The system’s part
Students were randomly assigned to placement by the algorithms or by the colleges' standard procedures, so the difference measures the placement system's effect. The algorithms weight a few factors fitted to each college's historical data. The authors of the 2025 follow-up describe them as regression models chosen by their fit to past data, and neither review describes machine learning. The study's authors report that students gained when placed in college-level courses, whatever the algorithms predicted.
Not yet checked
LimitsCosts and harmsLearns from dataLater outcome

Download data Cite Suggest a correction

Benefit type
Increased Access to Education
System
Multiple measures, data analytics placement system (predictive placement algorithms developed at each college)
Made by
Center for the Analysis of Postsecondary Readiness (Community College Research Center and MDRC) with each college
Used by
Seven SUNY community colleges: Cayuga, Jefferson, Niagara, Onondaga, Rockland, Schenectady and Westchester
Where
New York, United States
Stage
In a pilot
Date
Kind
Aggregate result
Broad benefit
Judging the Qualities of Objects, Services, or People, Making Decisions and Solving Problems
Collections
Scrutiny and findings
Last revised
1 November 2026

Sources

  1. Assessment report, by an evaluator that the makers or users commissioned.

    U.S. Department of Education, Institute of Education Sciences, What Works Clearinghouse. Single study review of Barnett, Kopko, Cullinan and Belfield (2020), Who Should Take College-Level Courses? Impact Findings from an Evaluation of a Multiple Measures Assessment Strategy. Reviewed August 2021. The Institute of Education Sciences funded the study (grant R305C140007).

    Predictive algorithms were developed separately at each college using historical data that weighted different factors such as placement test scores, high school GPAs, and time since high school graduation according to how well they predicted success in college-level math and English courses.

  2. Assessment report, by an evaluator that the makers or users commissioned.

    What Works Clearinghouse, Institute of Education Sciences, U.S. Department of Education. WWC review of this study (Study 95266, single study review, reviewed July 2026): Kopko EM, Daniels Sarica H. The long-term effectiveness of multiple measures assessment: Evidence from a randomized controlled trial. Journal of Research on Educational Effectiveness 19(2): 327-350, 2025. The Institute of Education Sciences funded CAPR, which built the formulas.

    College Readiness outcomes-Tier 1 (strong evidence) found for the domain

  3. Report, by the makers.

    Barnett EA, Kopko E, Cullinan D, Belfield CR. Who Should Take College-Level Courses? Impact Findings from an Evaluation of a Multiple Measures Assessment Strategy. Center for the Analysis of Postsecondary Readiness, October 2020. ERIC ED609173, abstract as provided by the authors.

    In math, gains in college-level enrollment and completion were small and short-lived. But in English, the effects were much larger and lasted through at least three semesters.

  4. Report, by the makers. Context or contrary evidence.

    Kopko E, Daniels H, Cullinan D. The Long-Term Effectiveness of Multiple Measures Assessment: Evidence From a Randomized Controlled Trial. A CAPR Working Paper. Center for the Analysis of Postsecondary Readiness, October 2023, revised March 2024, Appendix B. Supported by the Institute of Education Sciences through Grant R305C140007.

    Historical high school and placement test data were needed to create predictive algorithms at each college.

Details

AI system

Workflow

Each college fitted its algorithm to historical data, weighting placement test scores, high school GPAs and time since high school. Each college set its cut points from calculated misplacement rates.

Follow-up

Conditions for replication

Colleges need historical records of their own students' test scores, grades and course outcomes. Placement must let more students start in college-level courses, which is where the study's authors found the gains.

Entry details

Sector

Education.

Purpose

The Center for the Analysis of Postsecondary Readiness and seven SUNY community colleges built the placement algorithms to place entering students in remedial or college-level math and English courses.

30 more questions not yet checked

model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this record

Peter H. Vartanian. (2026). Data analytics placement lifts college English completion at SUNY (AIBD-1157). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-1157.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)

BibTeX Data Field definitions