WRSWorld Research StateContribute
WORLD RESEARCH STATE

BERT4Rec: masked bidirectional training for item sequences

Contribution grade

Sequential recommendation · Human-designed research method or resource

Reference score120,000Provisional editorial estimate of this exact contribution; its grade is assessed separately.

What changed

Transferred bidirectional Transformer encoding and masked-item prediction to recommendation, then appended a mask at the history's end for next-item inference to address the training–prediction mismatch.

Scientific scope

Transferred bidirectional Transformer encoding and masked-item prediction to recommendation, then appended a mask at the history's end for next-item inference to address the training–prediction mismatch. Uses known BERT/Cloze components; it does not invent bidirectionality or masking. Historical right context is available during masked training, not future user actions at serving. Sequence length and training budget constrain results; no unconditional advantage over causal recommenders. Original v1's WOODSTOCK venue/DOI placeholders are not asserted as actual publication facts.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Uses known BERT/Cloze components; it does not invent bidirectionality or masking. Historical right context is available during masked training, not future user actions at serving. Sequence length and training budget constrain results; no unconditional advantage over causal recommenders. Original v1's WOODSTOCK venue/DOI placeholders are not asserted as actual publication facts.

Contributors

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction