AIQF Daily digest — 18 new papers

Quant Paper Radar · 3 of 18

1. 1

   Reinforcement Learning with Hawkes-Structured Networks for Market Making

   Fernando Acero, Philipp Plank, Yufei Zhang · ARXIV · Market Making

   quant relevance 1.00

   The paper develops a reinforcement-learning policy for setting market-making quotes using Hawkes-filtered order-flow history. Its reported reward comparisons come from simulated market-making environments, not a backtest on real market data.

   original paper

2. 2

   Data-Driven Dynamic Portfolio Selection with Vine Copula Simulation and Reinforcement Learning

   Gabriël M. J. Gelissen, Fengyi Yuan · ARXIV · Dynamic portfolio allocation

   quant relevance 0.98

   The paper develops a vine-copula simulation and reinforcement-learning method for portfolio allocation with a CVaR penalty. It reports backtested growth, Sharpe ratio, and turnover for a seven-asset portfolio containing US and Chinese equities and gold.

   original paper

3. 3

   The Buffett Effect

   Pawel Robert Smolinski, Siddharth Saridevi · ARXIV · Event-driven disclosure copying

   quant relevance 0.95

   The paper tests whether newly disclosed stock positions of recognizable fund managers predict abnormal returns and reports performance from portfolios that copy those positions. The central trading signal requires manager-level Form 13F holdings and filing dates, which the platform does not have.

   original paper

15 more papers written up in this period. Open the Quant Paper Radar →