Auto-Prep: Holistic Prediction of Data Preparation Steps for Self-Service Business Intelligence
Summary: Auto-Prep jointly predicts data transformations and joins for self-service BI, recognizing their interdependence and modeling workflows via a Steiner-tree-inspired graph algorithm with quality guarantees. On ~2K real projects, it predicts over 70% of steps, outperforming prior methods and GPT-4. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Eugenie Y. Lai (Massachusetts Institute of Technology)
- 2. Yeye He (Microsoft)
- 3. Surajit Chaudhuri (Microsoft)
BibTeX Citation
@article{lai_vldb25,
title = {{Auto-Prep: Holistic Prediction of Data Preparation Steps for Self-Service Business Intelligence}},
author = {Lai, Eugenie Y. and He, Yeye and Chaudhuri, Surajit},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {14},
number = {7},
pages = {2212--2225},
doi = {10.14778/3734839.3734856},
url = {https://doi.org/10.14778/3734839.3734856},
year = {2025}
}
Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,202 | BAT: Target-Instance-Free Data Preparation Synthesis via LLM-Driven Tree Search | 2026 | SIGMOD | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 27 of 27 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next