AI-Trader benchmarks LLMs in live financial markets, revealing poor trading performance.
problem Challenges in real-time financial decision-making by autonomous agents.
method Fully automated, live evaluation benchmark with minimal human intervention.
result General intelligence does not translate to effective trading, highlighting limitations.
LiveTradeBench evaluates LLMs in live trading environments.
problem Static benchmarks fail to assess real-world trading ability.
method Live data streaming, portfolio management abstraction, multi-market evaluation.
result LLMs show distinct portfolio styles and adapt to live signals.
Backtests of structured strategies lose much of their predictive power in live trading.
problem Uncertainty in how marketed backtests predict live performance of structured strategies.
method Analysis of 1,726 structured strategies from ten global institutions.
result Raw backtests have limited portability into live trading and deteriorate sharply.
Under risk, Arrow-Debreu equilibria can be implemented as Radner equilibria by continuous trading of few long-lived securities. We show that this result generically fails if there is Knightian uncertainty in the volatility. Implementation is only possible if all discounted net trades of the equilibrium allocation are m…
This paper investigates the equilibrium interactions between trading targets and private information in a multi-period Kyle (1985) market. There are two investors who each follow dynamic trading strategies: A strategic portfolio rebalancer who engages in order splitting to reach a cumulative trading target and an uncon…
Market makers face a trade-off between fill probability and post-fill returns, requiring contrarian strategies.
problem Navigating the trade-off between fill probability and post-fill returns in market making.
method Analysis of live trading data from Binance Bitcoin perpetual.
result A negative correlation between maker fill likelihood and post-fill returns, necessitating contrarian strategies.
FinRL-X unifies trading components for AI and rule-based strategies.
problem Inconsistent between research and live deployment in trading platforms.
method Modular architecture integrating data processing, strategy construction, backtesting, and execution.
result Unified protocol supports AI and rule-based trading components without altering execution.
AGENTICAITA uses AI agents to autonomously trade markets without human intervention.
problem Inability of traditional trading systems to adapt to market complexity.
method Introduces an agentic AI framework with specialized LLM agents reasoning, negotiating, and acting.
result Demonstrated operational correctness and non-trivial inter-agent negotiation in live market conditions.
Study examines Bitcoin market fragmentation and price formation, revealing market leader-lagger dynamics and trading strategies.
problem Understanding price formation in fragmented Bitcoin markets at sub-second time scales.
method Utilized granular orderbook and trades data, constructed features, and trained linear models to explain market returns.
result Fee regime determines market leadership and profitability of taker strategies, maker strategies tested in real-world trading.
Research optimizes C++ patterns for HFT, reducing latency and improving profitability.
problem Optimizing latency-critical code for high-frequency trading systems.
method Creation of a Low-Latency Programming Repository, optimisation of trading strategy, implementation of Disruptor pattern.
result Significant performance improvements in speed and profitability.
Dynamic sentiment analysis improves stock trading strategies.
problem Improving stock trading performance through dynamic agent switching.
method Combining sentiment analysis with deep reinforcement learning and dynamic agent switching.
result Dynamic sentiment-based trading strategy outperforms traditional methods.
In this paper, we present a multi-period trading model in the style of Kyle (1985)'s inside trading model, by assuming that there are at least two insiders in the market with long-lived private information, under the requirement that each insider publicly discloses his stock trades after the fact. Based on this model, …
PolyBench benchmarks LLMs on real market data, revealing significant performance gaps.
problem Benchmarking LLMs for real-world event prediction from live market signals.
method Multimodal benchmark derived from Polymarket, evaluating 7 LLMs under identical market states.
result Only two models achieve positive financial returns, highlighting the gap between fluency and probabilistic reasoning.
Improved stock trading model using feature selection and ensemble learning.
problem Challenges in making profit in the US stock market.
method Feature selection from 148 to 30, dynamic selection of top 25 features, ensemble learning with four classifiers.
result Best model generated 54.35% profit over 18 months.
Agent Trading Arena trains LLMs in real-time financial markets to improve numerical reasoning.
problem Limited real-world training for LLMs in financial markets.
method Virtual zero-sum stock market with competitive multi-agent trading.
result LLMs perform better with chart-based visualizations and a reflection module.
This paper examines how wash traders exploit market conditions in Bitcoin, finding strategic timing and spillover effects.
problem Wash trading in cryptocurrency markets to inflate volume and manipulate market conditions.
method Analysis of 18 million Mt. Gox transactions, exogenous demand shock study.
result Wash trading intensifies in low legitimate trading volume and responds to demand shocks, indicating strategic behavior.
Quant firms manipulate stock markets overnight and intraday.
problem Unexplained consistent overnight and intraday returns in stock markets.
method Analysis of trading patterns and market movements.
result Large quant firms expand and contract portfolios to create mark-to-market gains.
FinRL automates trading in quantitative finance with deep reinforcement learning.
problem Steep development curve for traders to automate trading decisions.
method Open-source framework implementing DRL algorithms and reward functions.
result FinRL simplifies strategy design and reduces debugging workloads.
QTNet uses deep reinforcement learning to automate trading strategies.
problem Handling noisy and high-frequency financial data, balancing exploration and exploitation.
method QTNet employs deep reinforcement learning (DRL) with imitative learning to autonomously formulate trading strategies.
result QTNet demonstrates proficiency in extracting robust market features and adaptability to diverse conditions.
High-frequency trading models fail due to overfitting and survivor bias.
problem Failure of hybrid DRL-EC trading systems in high-frequency environments.
method Deployed a population of 500 agents in a high-frequency cryptocurrency environment, analyzing failure modes through multi-disciplinary lens.
result Increasing model complexity without information asymmetry exacerbates systemic fragility.
Pre-trained LLM adapted with LoRA improves offline RL for quantitative trading.
problem Challenges in offline RL for quantitative trading due to complex temporal dependencies and overfitting.
method Integrates pre-trained GPT-2 weights and LoRA for efficient fine-tuning of a Decision Transformer.
result Outperforms existing offline RL methods in certain trading scenarios.
Study creates a global living index to assess quality of life.
problem Long-term impacts of global economic changes on living conditions.
method Machine learning framework combining socio-economic factors.
result Developed a practical tool for policymakers to identify areas needing improvement.
Ensuring sufficient liquidity is one of the key challenges for designers of prediction markets. Various market making algorithms have been proposed in the literature and deployed in practice, but there has been little effort to evaluate their benefits and disadvantages in a systematic manner. We introduce a novel exper…
This paper questions some current ideas about the practice of specific capital market operations - the so-called day trading operations. The text advanced from theoretical propositions to a detailed analysis of the study entitled "Is it possible to live by day-trading?" (CHAGUE and GIOVANNETTI, 2019), to which it offer…
This paper describes the design, implementation, and successful use of the Bristol Stock Exchange (BSE), a novel minimal simulation of a centralised financial market, based on a Limit Order Book (LOB) such as is common in major stock exchanges. Construction of BSE was motivated by the fact that most of the world's majo…
Living review of ML for particle physics, updated frequently.
problem Keeping up with rapid advancements in ML for particle physics.
method Creating a living document to list and update citations of ML applications.
result Provides a comprehensive list of ML citations for particle physics.
Framework mitigates overfitting in quantitative trading strategies.
problem Overfitting during strategy transition from backtest to live trading.
method Three-stage protocol: IS, WFA, OOS; majority pass, purge gaps, cliff veto, etc.
result Demonstrates how to detect overfitting through performance decay and drawdown behavior.
This paper uses RL and RNN to optimize trading with latent market information.
problem Optimal trading strategies exploiting latent information in financial markets.
method Blend of RL and RNN, integrating GRU networks for temporal dependencies.
result prob-DDPG achieves superior cumulative rewards and interpretable strategies.
Study predicts global trade impacts using deep learning during the COVID-19 period.
problem Forecasting global trade impacts during the COVID-19 pandemic.
method Developed a sustainable prediction process using Long-Short Term Memory (LSTM) deep learning model.
result Accurately predicted daily imports and exports for the next 180 days during the pandemic.
Study models live cattle futures prices in Brazil.
problem Estimate futures prices for better risk management.
method Holt-Winters, ARIMA, GARMA models.
result GARMA(2,1) model best predicts BGI prices.
Driven by the tremendous technological advancement of personal devices and the prevalence of wireless mobile network accesses, the world has witnessed an explosion in crowdsourced live streaming. Ensuring a better viewers quality of experience (QoE) is the key to maximize the audiences number and increase streaming pro…
RED-2400 is a public benchmark of trading events from a Solana exchange, labeled by algorithmic rejection.
problem Analyzing algorithmically-rejected trading events for insights into market dynamics.
method Public dataset of 6,660 algorithmically-rejected trading events, linked to post-rejection price and liquidity trajectories.
result First window of a planned series of datasets extending the time horizon and enabling regime-stratified analysis.
BiCB combines traffic prediction and bidding optimization for live advertising.
problem Real-time bidding in live advertising with unknown future traffic.
method Binary Constrained Bidding (BiCB) that merges mathematical analysis and statistical traffic estimation.
result BiCB achieves good approximation to optimal bidding results with low complexity.
Model optimal growth strategy in a market with short-lived assets.
problem Investment market with short-lived assets and endogenous prices.
method Formulate stochastic equation for wealth processes and prove existence of optimal strategy.
result Existence of a submartingale strategy ensuring investor's wealth growth asymptotically.
The paper tackles dynamic collateral control for spot-perpetual basis trading in decentralized finance.
problem Dynamic control of collateral in spot-perpetual basis trading in decentralized finance.
method Solves a static control problem and derives an asymmetric dynamic extension, validated with live execution.
result The dynamic control approach provides a more robust operating benchmark and shows significant rebalancing effects.
PDLPs reduce borrowing costs for perpetual futures traders.
problem High capital costs for market makers and traders in decentralized settings.
method Formalize PDLPs and target weight mechanisms, describe pool arbitrage and expected payoffs.
result PDLPs are easy to delta hedge, improving capital efficiency.
Dynamic-weight AMMs outperform traditional CEX rebalancing in tokenized funds, especially on L2s.
problem Improving asset allocation efficiency in decentralized finance (DeFi) protocols.
method Block-level arbitrage analysis and long-term performance benchmarks on two live pools.
result Dynamic-weight AMMs can achieve performance comparable to or better than traditional CEX rebalancing, especially on Layer 2 (L2) networks.
Optimal strategies are found for a repeated betting game using diffusion approximation.
problem Finding optimal strategies for a repeated betting game with i.i.d. outcomes.
method Constructing a diffusion approximation of the repeated game and analyzing the wealth share process.
result Necessary and sufficient conditions for the wealth share process to be transient or recurrent are derived.
Multi-StyleGAN simulates live cell microscopy imagery.
problem Costly and complex live cell experiments.
method Generative adversarial network (GAN) synthesizing multi-domain time-lapse images.
result Captures biophysical factors and time dependencies in cell imagery.
As Convolutional Neural Networks embed themselves into our everyday lives, the need for them to be interpretable increases. However, there is often a trade-off between methods that are efficient to compute but produce an explanation that is difficult to interpret, and those that are slow to compute but provide a more i…
Predict human lives using sequences of life events.
problem Predicting human life outcomes based on detailed event sequences.
method Adapting natural language processing techniques to analyze life events.
result Models predict diverse outcomes with high accuracy, outperforming state-of-the-art models.
AlphaX uses AI to outperform Brazilian stock market benchmarks.
problem AI strategies often overperform in backtests but underperform in real markets due to lookahead bias.
method Controlled simulations to mitigate lookahead bias, using Value Investing principles.
result AlphaX strategy outperforms major benchmarks and technical indicators.
We tested in a live setting the use of active learning for selecting text sentences for human annotations used in training a Thai segmentation machine learning model. In our study, two concurrent annotated samples were constructed, one through random sampling of sentences from a text corpus, and the other through model…
Uniswap v3 LPs suffer significant Impermanent Loss despite higher fees.
problem Impermanent Loss in leveraged liquidity provision on Uniswap v3.
method Analysis of 17 pools covering 43% of TVL, calculating fees and IL.
result LPs would have been better off by $60.8m had they HODLd.
While historically, economists have been primarily occupied with analyzing the behaviour of the markets, electronic trading gave rise to a new class of unprecedented problems associated with market fairness, transparency and manipulation. These problems stem from technical shortcomings that are not accounted for in the…
Artificial intelligence, or AI, enhancements are increasingly shaping our daily lives. Financial decision-making is no exception to this. We introduce the notion of AI Alter Egos, which are shadow robo-investors, and use a unique data set covering brokerage accounts for a large cross-section of investors over a sample …
Study finds consumers are more price-sensitive before livestreams than after.
problem Understanding consumer demand during livestreaming lifecycle.
method Examined consumer demand for live events and recorded versions using data from a livestreaming platform.
result Demand is more price-sensitive before livestreams than after.
Agent-based model simulates market dynamics with real-time order matching.
problem Realistic simulation of market dynamics with realistic price impact.
method Agent-based model with asynchronous, event-time order matching.
result Realistic price impact curves and stylized facts presented.