Game theory models futures market dynamics with incomplete information.
problem Modeling competition and price dynamics in futures markets with incomplete information.
method Formalizes a multi-step, non-cooperative game for n players.
result Reduction in price gaps due to high competition improves market liquidity.
The paper proposes a new co-training method using information theory.
problem Predicting future sensations from past ones.
method Introduces a co-training objective based on mutual information.
result The method improves mutual information between past and future sensations.
This paper proposes a method for deep RL agents to explore less frequent states.
problem Efficient exploration in deep RL tasks, especially for high-dimensional image frames.
method A deep prediction model and a convolutional autoencoder model are trained to predict and hash future frames, respectively. A reliable metric for evaluating novelty is derived to inform exploration.
result The proposed method enables deep RL agents to explore less frequent states, leading to higher accumulative future return.
RNNs are suboptimal at compressing past sensory inputs for future prediction.
problem RNNs do not optimally compress past sensory inputs for future prediction.
method Investigated RNNs trained with maximum likelihood and found they extract unnecessary information. Injected noise into hidden states to improve performance.
result Injecting noise into RNN hidden states improves predictive information, sample quality, likelihood, and classification performance.
New findings show Markov models often miss past-future dependencies.
problem Markov models fail to capture dependencies between past and future.
method Investigates how much past-future information is hidden in the present.
result Markov models often miss dependencies between past and future.
We propose a mathematical procedure for finding informed traders in ultra-high frequency trading. We wrote it as Vector ARMA and found condition of its stationarity. For the price exposure complied with ARMA(1,2) we proved that underlying asset price difference can be derived as ARMA(1,1) process. For validation of the…
Paper quantifies how past stock returns inform about volatility and future returns.
problem Inferring volatility and future returns from past returns in stochastic volatility models.
method Quantifies mutual information between past and future stock returns and volatility.
result Past stock returns provide significant information about future volatility and returns.
Surveying future location and trajectory prediction methods for moving objects.
problem Growth of positioning technologies produces large tracking datasets.
method Extensive review of 50 works on predictive analytics for moving objects.
result Proposes a novel taxonomy of predictive algorithms.
Extracts credit-relevant information from earnings calls.
problem Investors do not fully internalize credit-relevant information from earnings calls.
method Develops a novel technique to extract credit-relevant information from earnings call text.
result The extracted information forecasts future credit spread changes and firm profitability.
Study optimal portfolios for traders with asymmetric information and delay.
problem Optimizing portfolios for traders with delayed insider information.
method Anticipating stochastic calculus and white noise approach.
result Optimal portfolios maximize expected logarithmic utility under various financial models.
Study identifies key trades predicting market movements.
problem Predicting future market price movements.
method Optimized neural network predictor to identify influential trades.
result Trades with specific characteristics significantly impact future price predictions.
GDT improves reinforcement learning by matching future state information efficiently.
problem Efficient learning of multi-task policies from trajectory data.
method Generalized Decision Transformer (GDT) for offline hindsight information matching.
result GDT enables effective offline multi-task state-marginal matching and imitation learning.
Proposes MLCNN for better multivariate time series forecasting.
problem Challenges in forecasting multivariate time series, especially the limitation of predicting only one future moment.
method MLCNN, a multi-task deep learning framework inspired by Construal Level Theory, fuses future visions of near and distant future predictions.
result Significant improvements in forecasting accuracy (4.59% RMSE reduction, 6.87% MAE reduction) on real-world datasets.
This work analyzes the value of future reward information in RL.
problem Analyzing the impact of knowing future rewards in reinforcement learning.
method Competitive analysis and worst-case reward distribution.
result Exact ratios between standard RL agents and those with future-reward lookahead.
This study examines lead-lag relationships in Chinese futures markets using high-frequency data.
problem Understanding high-frequency trading dynamics and information flow in futures markets.
method High-frequency tick-by-tick data analysis of lead-lag relationships between different maturity futures contracts.
result The near-month futures lead longer-dated contracts by one tick, with a negative feedback effect on the leading asset.
Model predicts future stock market structure using social and financial network data.
problem Predicting future stock market structure with high accuracy.
method Combines financial and social media network information using a multiplex network approach.
result Up to 40% out-of-sample performance improvement in predicting future market structure.
Graph neural controlled differential equations learn graph dynamics from vertex observations.
problem Predicting future states of dynamical systems on graphs with limited vertex data.
method Incorporates graph topology information into NCDE to predict graph dynamics.
result Informed NCDE requires fewer parameters and lower MAE compared to previous methods.
SPI detects anomalies using privileged information from training data.
problem Unsupervised anomaly detection in the absence of labeled test data.
method Constructs density estimates in privileged space and transfers them to anomaly scoring space.
result Significant improvement in anomaly detection performance with privileged information.
Proposes a multi-modal attention network for better stock price prediction.
problem Predicting future stock movements using historical records and social media.
method Extracts semantic information from social media, estimates credibility, and integrates with numeric features.
result Significantly improved prediction accuracy and trading profits compared to previous methods.
Dynamical-VAE learns causal dynamics from POMDPs using future information.
problem Learning accurate state representations from partial observations in POMDPs.
method Dynamical Variational Auto-Encoder (DVAE) with hindsight framework.
result DVAE uncovers causal graph more effectively than history-based methods.
Study finds financial YouTube channel 3PROTV predicts stock market performance and sentiment changes.
problem Determining the informational value of financial YouTube channels.
method Analyzing 3PROTV's content and its impact on stock market performance and sentiment.
result 3PROTV's content, particularly negative sentiment, predicts stock market performance and sentiment changes.
This paper introduces an information-based model for the pricing of storable commodities such as crude oil and natural gas. The model uses the concept of market information about future supply and demand as a basis for valuation. Physical ownership of a commodity is taken to provide a stream of convenience dividends eq…
The paper synthesizes the mathematics of modeling the future.
problem Modeling the future
method Unified mathematical synthesis
result Explicit connection of classical objects into a unified forecasting calculus
Study proposes a new approach to market dynamics using flow and liquidity data.
problem Tackles the challenge of predicting market direction from non-stationary price dynamics.
method Develops a new operator I=dV/dt to capture execution flow and uses eigenfunctions to infer price direction. result Demonstrates that the price impact concept is flawed and proposes an alternative method for directional prediction.
Calibrates carbon futures option pricing using high-frequency data.
problem Estimating equity and variance risk premia for carbon futures options.
method Multifactor stochastic volatility framework with jumps, employing indirect inference.
result Provides insights into carbon futures and option dynamics.
We find minimal sufficient statistics for two variables that preserve mutual information.
problem Preserving mutual information when variables have high dimensionality.
method Developed a method to replace each variable with a lower-dimensional representation while preserving mutual information.
result Minimal sufficient statistics can be used to replace both variables simultaneously, preserving mutual information.
PI-SAC agents learn predictive information to improve RL efficiency.
problem Improving sample efficiency in reinforcement learning.
method PI-SAC agents use a contrastive version of Conditional Entropy Bottleneck to learn predictive information from past and future states.
result PI-SAC agents significantly improve sample efficiency on challenging continuous control tasks.
The study extracts market direction from transaction data.
problem Extracting market direction from transaction data.
method Dynamic equation with time scale selection from past transactions.
result Automatic determination of time scale for price calculation.
The FSRM uses a multifractional process to capture price multifractality, revealing serial information for forecasting.
problem Capturing multifractal price dynamics for better forecasting.
method Developed a fractional stochastic regularity model based on multifractional processes and information theory.
result The serial information of the regularity process Ht can be theoretically determined, aiding in forecasting future price increments. New method for off-policy evaluation in POMDPs using future-dependent value functions.
problem Curse of horizon in off-policy evaluation for POMDPs.
method Develops future-dependent value functions and minimax learning method.
result PAC result and Bellman completeness for the proposed OPE estimator.
Analysts use vague language in reports to convey useful information about future payoffs.
problem Lack of precise numerical forecasts in analyst reports.
method Empirical analysis of analyst reports to assess the predictive power of linguistic tone.
result The textual tone of analyst reports has predictive power for forecast errors and subsequent revisions, especially when language is vague and uncertainty is high.
ChatGPT scores corporate investment plans, predicting future spending and returns.
problem Measuring and predicting corporate investment plans.
method Created a firm-level ChatGPT investment score based on conference calls.
result The investment score predicts future capital expenditures and returns.
MIRO learns robust latent spaces by maximizing mutual information with future information.
problem Robust perception in complex, unstructured environments with low sample complexity.
method MIRO maximizes mutual information in a latent space for model-based reinforcement learning.
result MIRO outperforms reconstruction objectives in cluttered scenes.
Investment strategies derived from commodity futures curves exploit dynamics in price movements.
problem Modeling and predicting the term structure of commodity futures prices.
method Employed the Nelson-Siegel framework to model term structure, and developed investment strategies based on changes in slope and curvature parameters.
result Significant profits generated from systematic strategies based on the change in slope, unrelated to risk factors and robust to transaction costs.
The study examines how global economic policy uncertainty affects crude oil futures volatility.
problem Predicting crude oil futures volatility using global economic policy uncertainty.
method Established single-factor and two-factor models under the GARCH-MIDAS framework, tested with rolling-window and fixed-span specifications.
result GEPU changes have stronger predictive power than the GEPU index for crude oil futures volatility.
Study examines grain futures connectedness during Russia-Ukraine conflict.
problem Quantile return connectedness of grain futures markets during geopolitical instability.
method Dynamic quantile VAR combined with frequency-domain decomposition.
result Heterogeneous spillovers across quantiles, with strong transmitters and persistent receivers.
This paper reviews information theory in open-world machine learning.
problem Lack of a unified theoretical foundation for open-world machine learning.
method Synthesis of information theoretic approaches.
result Established a pathway toward provable and trustworthy open world intelligence.
We study the problem of what causes prices to change. We define the mechanical impact of a trading order as the change in future prices in the absence of any future changes in decision making, and its it informational impact as the remainder of the total impact once mechanical impact is removed. We introduce a method o…
PAGAN uses GANs to model market uncertainty for better portfolio optimization.
problem High market efficiency makes traditional prediction models ineffective.
method Generative Adversarial Networks (GANs) to model market uncertainty.
result PAGAN optimizes portfolios by minimizing risk and maximizing returns.
Study shows using time-series privileged information improves model efficiency.
problem Efficiently predicting future outcomes using supervised models with privileged information.
method Developed an algorithm for learning with privileged time-series data and proved its efficiency for non-stationary Gaussian-linear systems.
result Learning with privileged information is more efficient than without it for non-stationary Gaussian-linear systems.
Investor optimizes stock investments with noisy future price signals.
problem Optimizing stock investments with uncertain future stock prices.
method Dynamic investment strategy with partial observation of Brownian motion.
result Closed-form solution for optimal investment problem.
Hierarchical graph learning for calendar spread strategies in commodity futures markets
problem Developing machine-learning methods for calendar spread strategies in commodity futures markets
method Proposing a hierarchical graph learning approach
result Outperforming benchmark models in both prediction and trading performance
Memory affects how we perceive time and make decisions about the future.
problem Temporal distortions and intertemporal choice preferences in humans and non-human subjects.
method Combining information theory and artificial intelligence, the study explains these phenomena through sensorimotor representation coding efficiency.
result Memory constraints lead to a renormalization of perceived timescales, resulting in different discount functions.
Measures information in neural networks via weights and activations.
problem Understanding how information is encoded and used in deep neural networks.
method Measures information via the optimal trade-off between accuracy and complexity of weights, defined by coding length.
result Establishes a relation between information in weights and effective information in activations, showing low complexity models generalize better and learn invariant representations.
We analyze the time series of overnight returns for the bund and btp futures exchanged at LIFFE (London). The overnight returns of both assets are mapped onto a one-dimensional symbolic-dynamics random walk: The `bond walk'. During the considered period (October 1991 - January 1994) the bund-future market opened earlie…
Machine learning predicts criminal networks' missing partnerships and future behavior.
problem Predicting and understanding criminal networks' properties and future behavior.
method Combining graph representation learning and machine learning methods.
result Outstanding accuracy in predicting missing criminal partnerships and future behavior.
Local volatility model for commodity futures options with online calibration.
problem Valuation and calibration of options on commodity futures.
method Local volatility model, online calibration, model-based price adjustment, Tikhonov regularization.
result Improved option valuation and smile adherence through online calibration and regularization.
Wind energy producer optimizes trading policies using updated forecasts.
problem Maximizing profit from wind energy sales in various markets.
method Stochastic model for forecast evolution, dynamic trading policies.
result Quantifies expected future gain and forecasts' economic value.