Chimera: Large-Scale Classification using Machine Learning, Rules, and Crowdsourcing

Summary: Chimera classifies tens of millions of products into 5,000+ types by integrating machine learning, analyst-authored rules, and crowdsourcing. Its WalmartLabs deployment shows that scale invalidates conventional assumptions, making hybrid workflows and large-scale rule management essential for accuracy, cost, and continual improvement. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID: 11001
Venue: VLDB
Year: 2014
Pagerank: 8.9303727e-05
Overall Rank: 2,219 | 84.78%
DOI: 10.14778/2733004.2733024

Incoming Non-self Citations Over Time

Authors

1. Chong Sun (WalmartLabs)
2. Narasimhan Rampalli (WalmartLabs)
3. Frank Yang (WalmartLabs)
4. AnHai Doan (University of Wisconsin; WalmartLabs)

BibTeX Citation

@article{sun_vldb14,
        title = {{Chimera: Large-Scale Classification using Machine Learning, Rules, and Crowdsourcing}},
        author = {Sun, Chong and Rampalli, Narasimhan and Yang, Frank and Doan, AnHai},
        journal = {PVLDB},
        series = {{VLDB} '14},
        volume = {7},
        number = {13},
        pages = {1529--1540},
        doi = {10.14778/2733004.2733024},
        url = {https://doi.org/10.14778/2733004.2733024},
        year = {2014}
}

Incoming Citations (Sorted by Pagerank)

Showing 10 of 10 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
4,610	Top-k Sorting Under Partial Order Information	2018	SIGMOD	6.6079578e-05
6,068	Why Big Data Industrial Systems Need Rules and What We Can Do About It	2015	SIGMOD	5.9887211e-05
8,351	Minimizing Efforts in Validating Crowd Answers	2015	SIGMOD	5.4454221e-05
8,788	Managing General and Individual Knowledge in Crowd Mining Applications	2015	CIDR	5.3726124e-05
8,855	ANN Softmax: Acceleration of Extreme Classification Training	2022	VLDB	5.3573227e-05
10,112	Classifier Construction Under Budget Constraints	2022	SIGMOD	5.1319012e-05
11,777	MC3: A System for Minimization of Classifier Construction Cost	2020	SIGMOD	5.093636e-05
11,790	Minimization of Classifier Construction Cost for Search Queries	2020	SIGMOD	5.093636e-05
11,806	CONCIERGE: Improving Constrained Search Results by Data Melioration	2020	VLDB	5.093636e-05
11,822	Exploiting Domain Knowledge to address Multi-Class Imbalance and a Heterogeneous Feature Space in Classification Tasks for Manufacturing Data	2020	VLDB	5.093636e-05

Outgoing Citations (Sorted by Pagerank)

Showing 1 of 1 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
439	Corleone: Hands-Off Crowdsourcing for Entity Matching	2014	SIGMOD	0.00018464913

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	7,357	Crowdsourced Data Management: Overview and Challenges	2017	SIGMOD
2	1,791	Cheetah: A High Performance, Custom Data Warehouse on Top of MapReduce	2010	VLDB
3	6,038	Efficient Construction of Approximate Ad-Hoc ML models Through Materialization and Reuse	2018	VLDB
4	4,812	Clustering by Pattern Similarity in Large Data Sets	2002	SIGMOD
5	3,714	Large-Scale Machine Learning at Twitter	2012	SIGMOD
6	6,908	Cost-Effective Data Annotation using Game-Based Crowdsourcing	2019	VLDB
7	4,859	Machine Learning for Big Data	2013	SIGMOD
8	8,495	CrowdGame: A Game-Based Crowdsourcing System for Cost-Effective Data Labeling	2019	SIGMOD
9	2,626	Scaling Up Crowd-Sourcing to Very Large Datasets: A Case for Active Learning	2015	VLDB
10	6,068	Why Big Data Industrial Systems Need Rules and What We Can Do About It	2015	SIGMOD