Papers for

market operators

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

State aligned order flow interventions improve low risk trading costs

When and How Order-Flow Interventions Work After Dealers Adapt

Abstract: Learning dealer agents can settle on persistently wide quotes, raising what customers pay to trade. A venue can route more orders to tighter quotes, but a wide quote may reflect real risk, and once dealers adapt, an end-to-end comparison cannot show why a rule works: because it intervenes more, picks better moments, is announced in advance, or rewards the right quote. We propose SOFA (State-aligned Order-Flow Allocation), a public order-flow contract with three parts: a State Scorer ranks market states from lagged public data, a Commitment Scheduler announces a budgeted intervention strength before dealers quote, and a Quote-to-Flow Allocator shifts a bounded share of fixed customer demand toward tighter quotes. Our paired re-adaptation protocol gives competing rules the same intervention strengths, only re-timed, lets dealers re-adapt to each rule from a shared checkpoint, and breaks one link at a time. Across 20 independently trained dealer populations in an ABIDES market, concentrating the intervention in states that the score ranks as low-risk lowers low-risk execution cost relative to random timing in every population, by 0.040 tick on average, while a stale announcement or a broken quote-to-flow link raises this cost. In the primary setting the gain comes at the expense of high-risk trades, whose costs rise, so state alignment pays off only for a venue that weighs low-risk costs more than 1.38 times as heavily as high-risk costs. Our code is available at https://github.com/moderncavemann/state-aligned-order-flow-contracts.

Tue 13 OctArtificial Intelligence
The gist
Trading platforms use dealers who set prices for orders, but sometimes these dealers keep prices high to protect themselves from risk, making trades more expensive for customers. The authors show that by focusing interventions on market states identified as low risk, platforms can lower the cost of trades in those good times without making broad changes that don't consider risk levels. They propose a method called SOFA that ranks market risk, plans when to intervene, and reallocates orders toward better prices. Their experiments show this targeted approach lowers costs in low-risk states but may increase costs during risky periods, so it works best for venues valuing low-risk trade improvements more highly.
Open → 2610.18158v1

Polymarket weather forecasts bias shifts from longshots to favorites over time

Time-Varying Favorite-Longshot Bias in Polymarket Weather Markets

Abstract: Prediction-market prices combine traders' judgments about future outcomes, but their errors may be concentrated in particular price ranges and change as settlement approaches. Prior cross-category evidence shows that Polymarket weather markets have larger pricing bias than other major categories, without separating low-price longshots from high-price favorites. This study compares the two ranges at different horizons in daily maximum-temperature markets. Event-level probability scores, cubic B-spline recalibration, and Buy-NO tests are used to examine the form and effect of the bias. Longshot overpricing mainly occurs at distant horizons, whereas favorite overpricing becomes much stronger during the final 1-12 hours and is nearly one order of magnitude larger. Event-level scores improve toward the daily temperature peak, while simple recalibration yields no statistically significant gains. The Buy-NO results in the corresponding time windows also show that the main pricing error is concentrated at the favorite end.

Fri 9 OctDatabases
The gist
Prediction markets where people bet on weather outcomes sometimes misprice probabilities. This study finds that bets on unlikely weather events are priced too high far in advance, but as the weather event gets closer, bets on more likely outcomes become overpriced instead. The biggest bias happens just hours before the event, especially for favorites. Attempts to correct these biases using simple methods weren't clearly effective. The authors use special scoring and tests to analyze these changing biases over time.
Open → 2610.13593v1