NUS operations researcher linking exact pricing optimization with LLM-agent methods for retail supply chain operations
2
papers here
2
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
—
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-16) and cover the author's entire public record, not just the papers listed here. Reproducibility signal comes from Evolve's own reviews.
Research profile
Output—
Not yet scored: the bibliometric snapshot provides no publication-count or output-volume data for this researcher. This axis would measure total research output over time, including paper counts by year and venue type, before any productivity assessment can be made.
Impact—
Not yet scored: no citation counts or other impact metrics appear in the provided data. This axis would measure scholarly influence through citations and downstream use, and is not estimated from the two reviewed papers.
Focus0/100
Scores 0, reflecting the even field distribution in the raw data: 50% machine-learning methods for operations research and revenue management, 50% LLM-based agents for supply chain optimization. The two reviewed 2026 papers split across these directions — one on exact choice model trees for pricing, one on agentic warehouse reformulation — so the portfolio is dual-track rather than concentrated in a single field.
Collaboration44/100
Scores 44 out of 100, based on 8 distinct coauthors recorded in the bibliometric snapshot. Both reviewed 2026 papers are team efforts with him in the last author position, consistent with a senior authorship role, spanning two separate collaboration groups: one around the choice-model pricing work and one around the LLM-agent supply chain study. Named frequent coauthors include Lei Zheng, Liping Yang, Zihao Li, Guodong Lyu, Chaik Ming Koh, Jiajie Zhang, Yanqiu Ruan and Xiao Jin.
Activity—
Not yet scored: the snapshot contains no yearly publication-activity data beyond the two 2026 arXiv papers. This axis would measure publishing cadence and recent momentum; with only a single year represented, no trend or activity level can be computed.
Reproducibility38/100
Scores 38, the mean reproducibility readiness across 2 assessed papers. The choice-model-tree paper rates medium: the optimization theory via dynamic programming and Fenchel duality is rigorous, but its field RCT lacks an active algorithmic baseline. The agentic supply chain paper rates low, with reported gains (ESR 72-76% to 79-83% on 100 requirements) unsupported by significance tests or ablations.
Research summary
Chung Piaw Teo is a researcher at the National University of Singapore whose recent work, as captured in Evolve's catalog, sits at the interface of operations research and machine learning. The catalog holds two 2026 arXiv papers, both with him in the last author position. The first, on learning choice model trees for feature-based multi-product pricing, presents what Evolve's review describes as the first exact optimal choice model tree with multinomial logit leaves, using dynamic programming and Fenchel duality, supported by synthetic experiments and a field RCT. The second applies LLM-based agents to retail supply chain operations, introducing a graph-constrained agentic framework with hierarchical routing and execution-based selection that lifts warehouse reformulation ESR from 72-76% to 79-83% on 100 requirements. His radar profile shows an even 50/50 split between machine-learning methods for revenue management and LLM-agent approaches to supply chain optimization, with 8 distinct coauthors across the two papers and a reproducibility mean of 38 from 2 assessed papers. Both reviewed papers carry reproducibility caveats — a field RCT without an active algorithmic baseline in one, and missing significance tests and ablations in the other — so this profile should be read as an early snapshot of a senior, team-based research agenda rather than a complete record.
Collaboration pattern
Within the reviewed scope, collaboration is compact and team-based: 8 distinct coauthors (collaboration score 44/100), with Lei Zheng, Liping Yang, Zihao Li, Guodong Lyu, Chaik Ming Koh, Jiajie Zhang, Yanqiu Ruan and Xiao Jin appearing as frequent coauthors. On both 2026 papers he takes the last author position, suggesting the two efforts run as separate teams — one on exact pricing optimization, one on LLM-agent supply chain systems — rather than a single recurring group.
Research keywords
Highlights
First exact optimal choice model tree for feature-based pricing
Graph-constrained agentic AI lifts warehouse reformulation ESR
Last-author role across two AI-for-operations research lines
On both 2026 catalog papers he is the last author, spanning exact optimization for revenue management and LLM-agent methods for retail supply chains, supported by 8 distinct coauthors in the bibliometric snapshot.
Timeline
- 2026Posts 'Learning Choice Model Trees for Feature-Based Multi-Product Pricing: Exact Optimization and Field Evidence' to arXiv, in the last author position.
- 2026Posts 'Adapting to Evolving Requirements: Agentic AI for Retail Supply Chain Operations' to arXiv, also as last author.
- 2026Both papers enter the Evolve catalog, with reproducibility readiness rated medium and low respectively and an overall reproducibility mean of 38.
Papers in the Evolve catalog
Frequent co-authors
About this profile
This profile is AI-structured by Evolve.Pub from public bibliographic data (OpenAlex) and Evolve's own paper reviews. It is not written or endorsed by the researcher unless the profile is claimed. Radar dimensions are computed from real bibliometrics with fixed formulas — raw figures are shown alongside; missing dimensions mean insufficient data, never zero. Errors? Claim the profile to correct or hide it.
- Radar axes output, impact and activity are unscored: the bibliometric snapshot lacks publication counts, citation metrics and yearly activity data.
- Scope is limited to two Evolve-reviewed 2026 arXiv preprints; earlier or unindexed work is not reflected in this profile.
- The reproducibility score (38) rests on only two papers, rated medium and low, so it should be read as provisional.
- Identity is anchored to ORCID 0000-0002-0534-6858; country is not recorded, and both papers show him as last author without a corresponding-author flag.