saisrivatsan/deep-opt-auctions

Implementation of Optimal Auctions through Deep Learning

48
/ 100
Emerging

This project helps auction designers determine the best rules for selling items to bidders, especially when the bidders' preferences are complex or unknown. You input the types of items for sale (e.g., one item, multiple items, specific value distributions) and bidder behaviors (e.g., single bidder, multiple bidders with additive or unit-demand valuations). The output is an optimized auction mechanism, often visualized through allocation probability plots, that aims to maximize revenue or efficiency. This is for economists, market designers, and researchers in auction theory.

134 stars. No commits in the last 6 months.

Use this if you are an auction theorist or market designer looking to explore and implement optimal auction mechanisms for various item and bidder configurations using deep learning.

Not ideal if you need a plug-and-play solution for running an actual online auction with real-time bidding, as this is a research implementation for theoretical exploration.

auction-theory market-design economic-modeling mechanism-design optimization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

134

Forks

46

Language

Jupyter Notebook

License

MIT

Last pushed

Nov 24, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/saisrivatsan/deep-opt-auctions"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.