arXiv research

Study optimal pricing and inventory control in dynamic settings with censored demand.

A new method for inventory control using in-context learning and generative models.

We propose a continuous-time stock-flow consistent model for inventory dynamics in an economy with firms, banks, and households. On the supply side, firms decide on production based on adaptive expectations for sales demand and a desired level of inventories. On the demand side, investment is determined as a function o…

MaxCOSD algorithm tackles non-i.i.d. demands and stateful dynamics in online inventory control.

This paper tackles inventory control with general arrival dynamics and post-processing, improving profitability.

A contextual bandit method evaluates and improves inventory control policies.

Optimistic pricing algorithm handles online dynamic pricing with censored demand.

Model analyzes RFQ markets using stochastic control to optimize dealer performance and inventory.

Paper combines RL with policy regularization for inventory policies.

Many retailers today employ inventory management systems based on Re-Order Point Policies, most of which rely on the assumption that all decreases in product inventory levels result from product sales. Unfortunately, it usually happens that small but random quantities of the product get lost, stolen or broken without r…

Optimal vehicle repositioning policy found for shared mobility services.

Study on inventory control with changing demand, proposing adaptive algorithms.

A new approach integrates inventory prediction and routing optimization for better supply chain management.

We study the cross-correlation matrix $C_{ij}$ of inventory variations of the most active individual and institutional investors in an emerging market to understand the dynamics of inventory variations. We find that the distribution of cross-correlation coefficient $C_{ij}$ has a power-law form in the bulk followed by …

A PID-based feedback-control system improves multiple KPIs in RTB display advertising.

Study visualizes actor-critic loss landscapes for inventory optimization.

Unified framework connects two market-making models, revealing their underlying equivalence.

Optimal hidden-target learning for online inventory optimization on general convex sets.

Investigates market dynamics with informed traders and high-frequency traders.

A new algorithm avoids worst-case outcomes in risky contexts.

Develops methods for dynamic pricing in incomplete data settings.

Apparently random financial fluctuations often exhibit varying levels of complexity, chaos. Given limited data, predictability of such time series becomes hard to infer. While efficient methods of Lyapunov exponent computation are devised, knowledge about the process driving the dynamics greatly facilitates the complex…

New method learns credit prices offline without interaction.

New method reduces inventory inaccuracies by 10x, saving retailers 4% annually.

Paper analyzes sample complexity for offline RL with deep ReLU networks.

The paper proposes autoregressive models for better offline RL.

A dealer manages quotes and rejection rules to control slippage risk in FX markets.

BOMS enhances offline MBRL by improving model selection with Bayesian optimization.

We consider a repeated newsvendor problem where the inventory manager has no prior information about the demand, and can access only censored/sales data. In analogy to multi-armed bandit problems, the manager needs to simultaneously "explore" and "exploit" with her inventory decisions, in order to minimize the cumulati…

Algorithm learns optimal dynamic mechanisms from data.

Study on inventory management under uncertainty using smooth ambiguity preference.

Modeling option market making with hedging-induced price impact.

Proposes EDESH-SA for better inventory management under uncertainty.

Bayesian nonparametrics enables dynamic skill discovery from expert data.

MOOSE improves offline RL robustness by using dynamics models.

Identifies latent actions and dynamics from offline data with diverse demonstrators.

Bayesian optimization improves forest inventory sampling using remote sensing data.

In this paper we extend the market-making models with inventory constraints of Avellaneda and Stoikov ("High-frequency trading in a limit-order book", Quantitative Finance Vol.8 No.3 2008) and Gueant, Lehalle and Fernandez-Tapia ("Dealing with inventory risk", Preprint 2011) to the case of a rather general class of mid…

New method learns policies from offline data using operator models.

Study finds inventory inaccuracies are linked to store activity and product perishability.

Optimal market making strategy with price forecasts reduces inventory costs and spreads.

A new algorithm uses IVs to learn optimal policies from observational data.

Model analyzes competitive pricing strategies in large markets of perishable products.

New algorithms tackle robust RL with linear models, revealing unique challenges.

Proposes a method to learn policies from offline data with reduced bias.

The paper tackles reward-relevance in offline RL with sparse decision dynamics.

MOPO optimizes offline RL by penalizing dynamics uncertainty.

In this paper we complete and extend our previous work on stochastic control applied to high frequency market-making with inventory constraints and directional bets. Our new model admits several state variables (e.g. market spread, stochastic volatility and intensities of market orders) provided the full system is Mark…