Detects malicious accounts in permissionless blockchains using graph properties and ML.
problem Identifying and classifying malicious accounts in permissionless blockchains.
method Temporal graph properties, ML algorithms (ExtraTreesClassifier, K-Means), cosine similarity, behavior change analysis.
result ExtraTreesClassifier performs best in detecting malicious accounts on Ethereum blockchain.
Paper presents a new time-series segmentation technique for mobile phone user behavior.
problem Current segmentation techniques do not accurately capture individual user behavior over time.
method Behavior-Oriented Time Segmentation (BOTS) technique that considers temporal coverage and number of incidences.
result BOTS technique better captures user behavior at various times of day and week.
Despite the availability of very detailed data on financial market, agent-based modeling is hindered by the lack of information about real trader behavior. This makes it impossible to validate agent-based models, which are thus reverse-engineering attempts. This work is a contribution to the building of a set of styliz…
Cluster analysis of credit card accounts helps assess risk levels.
problem Assessing risk levels for credit accounts.
method Parametric modelling of account behavior, behavioral cluster analysis with a new dissimilarity measure.
result Interesting clusters and superior prediction of account default.
Quantitative analysis of order-splitting behavior in Japanese stock market.
problem Understanding and quantifying the order-splitting behavior of traders in the Japanese stock market.
method Analysis of a large dataset of trading accounts over nine years, clustering traders into order-splitting and random traders, and applying statistical methods to analyze metaorder length and sign correlation.
result The metaorder length distribution follows power laws with exponent α, and the sign correlation exponent γ is approximately α-1, supporting the LMF model.
Unified Bayesian model explains in-context learning and activation steering in LLMs.
problem Understanding and controlling the behavior of large language models (LLMs) through prompts and activations.
method Developed a Bayesian model to explain and predict the effects of in-context learning and activation steering.
result Unified model predicts distinct phases and sudden shifts in LLM behavior, explaining prior empirical phenomena.
Model shows traders' swarm behavior in markets with subjective predictions.
problem Understanding swarm behavior in markets with traders having subjective market predictions.
method Combination of priority queueing model and mean field theory, nonlinear Markov model.
result Swarm behavior emerges due to traders' reactions to market conditions, not their subjective predictions.
Study identifies key health behaviors linked to adolescent suicide attempts.
problem Understanding health behaviors associated with increased risk of adolescent suicide attempts.
method Cross-sectional data analysis using machine learning algorithms and logistic regression.
result Non-parametric Bayesian tree ensemble model outperforms other models, achieving 80.0% accuracy in goodness-of-fit and 78.2% in predictive accuracy.
New model accounts for continuous human trajectories in robotics.
problem Inaccurate probabilistic models of human behavior in robotics.
method Developed a new probabilistic model that considers distances between continuous trajectories.
result The new model outperforms existing models in explaining human behavior and improving robot inference.
We consider the asymptotic behavior of properly embedded minimal surfaces in the product of the hyperbolic plane with the line, taking into account the fact that there is more than one natural compactification of this space. This provides a better setting in which to consider the general problem of determining which cu…
Method learns driver behavior from synthetic data.
problem Learning driver behavior from unobservable variables.
method Simultaneous policy learning and latent state inference.
result Effective driving policies learned without direct class knowledge.
The tail behavior of BEKK-ARCH processes is studied, showing geometric ergodicity and regular variation.
problem Understanding the tail behavior of multivariate conditionally heteroskedastic processes.
method Geometric ergodicity and vector scaling regular variation are used to characterize the tail behavior of BEKK-ARCH processes.
result The invariant distribution of BEKK-ARCH processes is regularly varying, with different tail indices possible.
Cryptocurrency traders increase stock risk-seeking behavior.
problem Understanding the motivations behind cryptocurrency trading.
method Individual-level brokerage data analysis of stock trading behavior.
result Cryptocurrency traders increase risk-seeking behavior in stocks when engaging in cryptocurrency trading.
The paper finds a pervasive and severe bias in accounting semi-identity models.
problem Bias in investment-cash flow sensitivity models.
method Augmented specification with a bias-capturing variable tested across multiple databases.
result The Accounting Semi-Identity (ASI) distortion is universal and severe, affecting 100% of databases and explaining more than 83% of total explained variance.
The paper shows how ignoring temporal context in recommender systems evaluation leads to false confidence, proposing a method to embed temporal context.
problem The discrepancy between offline and online recommender system performance evaluation.
method Proposes a training procedure to embed temporal context into recommender systems and validates its advantage using multi-objective optimization.
result Including temporal context in recommender systems evaluation can improve recall@20 by up to 20%.
Paper improves off-policy evaluation by estimating behavior policy.
problem Evaluating policies with data from a different behavior policy.
method Importance sampling with an estimated behavior policy.
result Estimating behavior policy reduces mean squared error.
We provide a rigorous definition of the visual cause of a behavior that is broadly applicable to the visually driven behavior in humans, animals, neurons, robots and other perceiving systems. Our framework generalizes standard accounts of causal learning to settings in which the causal variables need to be constructed …
We give a stochastic microscopic modelling of stock markets driven by continuous double auction. If we take into account the mimetic behavior of traders, when they place limit order, our virtual markets shows the power-law tail of the distribution of returns with the exponent outside the Levy stable region, the short m…
Proposes a graph-based system for personalized news recommendation considering multiple user behaviors.
problem Lack of considering multiple user behaviors in news recommendation systems.
method Builds an interaction behavior graph, applies DeepWalk and G-CNN for news and behavior sequence representations, introduces core and coritivity features.
result Achieves personalized news recommendation considering user's concentration degree of interests.
We develop a framework for analyzing extreme values in correlated financial data.
problem Quantifying and mitigating risk in complex financial systems.
method Developed a practical framework for handling finite, multivariate, and correlated time series in finance.
result We successfully analyze high-frequency stock returns using univariate extreme value tools.
Researchers analyze tagging patterns on Stack Exchange communities.
problem Understanding the structure and evolution of tags in Q&A platforms.
method Empirical analysis and development of a generative model for tag co-occurrence.
result The model can reproduce statistical properties of co-tagging graphs.
Optimizes sparse mean-reverting portfolios for higher returns.
problem Finding optimal stock weights for mean-reverting portfolios.
method Transformed optimization problem into SDP, added constraints.
result Sparse mean-reverting portfolios provide higher returns with transaction costs.
Proposes BehavDT model for context-aware user behavior prediction.
problem Building a context-aware predictive model based on diverse user behavioral activities.
method Introduces BehavDT, a behavioral decision tree that considers user behavior-oriented generalization.
result BehavDT model outperforms traditional machine learning approaches in predicting user diverse behaviors considering multi-dimensional contexts.
FLARKO uses LLMs, KGs, and KTO to generate profitable, behaviorally aligned financial recommendations.
problem Financial recommendation systems often fail to account for behavioral and regulatory factors.
method FLARKO integrates LLMs, KGs, and KTO to generate profitable and behaviorally aligned recommendations.
result FLARKO consistently outperforms state-of-the-art recommendation baselines on behavioral alignment and joint profitability.
CalBehav models individual smartphone user behavior for calendar events.
problem Static calendar models do not reflect individual user behavior.
method Machine learning, context-aware, personalized model using time-series smartphone data.
result Data-driven model more effective for managing incoming mobile communications.
A framework for goal-based investing with penalties for fund transfers.
problem Investors' mental accounting and multiple investment goals.
method Continuous-time portfolio selection with mental costs and penalties.
result The value function is the unique solution to a complex system of equations.
Paper finds significant impact of stock market swings on equity risk premium predictability.
problem Predicting equity risk premium based on stock market behavior changes.
method Introduced Bullish Index and used FDMAA for returns analysis; considered 28 indicators.
result Positive shocks in Bullish Index correlate with strong equity risk premium predictability for up to six months, while negative shocks correlate for up to nine months.
Paper improves teaching by considering learner's preferences and constraints.
problem Teaching without considering learner's preferences and constraints.
method Design of learner-aware teaching algorithms that account for learner's preferences and constraints.
result Significant performance improvements over learner-agnostic teaching.
A new method detects fraud transactions by analyzing user behavior over time.
problem Detecting fraud transactions in online payment platforms.
method A time attention based recurrent layer framework combining static and dynamic user behaviors.
result Our method outperforms state-of-the-art methods, especially in recall at top percent.
BlockFLow ensures privacy and accountability in federated learning.
problem Malicious agents can weaken federated learning models.
method Differential privacy, auditing mechanism, Ethereum smart contracts.
result Audit scores reflect the quality of honest agents' datasets.
Method learns evolving policies in healthcare contexts.
problem Understanding non-stationary behavior in evolving decision-making processes.
method Inverse Contextual Bandits (ICB) approach for learning interpretable representations of non-stationary behavior.
result Demonstrated applicability and accuracy of ICB method in liver transplantation policies.
The study creates user personas based on user tenure and behavior for VoD streaming.
problem Understanding evolving user behavior in streaming services without explicit user profiles.
method Construct user personas using tenure timelines and temporal behavioral features.
result Personas provide stable and interpretable insights into user behavior evolution.
NAS model improves social recommendation accuracy using neural attention.
problem Capturing and weighing friends' preferences in social recommendation systems.
method Proposes a Neural Attention mechanism (NAS) for Social collaborative filtering.
result NAS model outperforms state-of-the-art methods in publicly available datasets.
Pandora hybridizes human and machine methods to explain AI system failures.
problem Understanding and explaining failures in complex AI systems.
method Hybrid human-machine methods and tools for summarizing system malfunction.
result Detailed performance views help in analysis and debugging of AI systems.
Models analyze how different levels of tax evasion affect income distribution.
problem Effects of varying levels of tax evasion on income distribution.
method Microscopic models of economic interactions with a tax system and redistribution.
result Gini inequality index increases with higher evasion levels, but evasion spread does not significantly affect it.
AI bias arises from human-defined goals, not algorithmic flaws.
problem AI bias due to human-defined goals in LLMs.
method Purpose-conditioned cognition and revealing downstream use of LLM outputs.
result AI bias can be reduced by purpose-aware prompting but not fully by regularization.
Improved Naive Bayes for better phone call behavior classification.
problem Noise in mobile phone data affects phone call behavior classification accuracy.
method Improved naive Bayes classifier with behavioral pattern analysis and dynamic noise threshold.
result Our technique improves classification accuracy by 15%.
Multifractal processes are a relatively new tool of stock market analysis. Their power lies in the ability to take multiple orders of autocorrelations into account explicitly. In the first part of the paper we discuss the framework of the Lux model and refine the underlying phenomenological picture. We also give a proc…
This paper uses probability tensors for efficient path planning in complex scenarios.
problem Efficient path planning in complex environments with obstacles and multiple goals.
method Probability tensors are used to model agent motion and decision-making, incorporating past and future information.
result The model finds solutions in complex scenarios, demonstrating realistic emergent behaviors.
New IRL framework divides behavior into subgoals for better prediction.
problem Handling changing intentions and diverse trajectories in reinforcement learning.
method Nonparametric spatio-temporal subgoal modeling for more efficient and compact behavior representation.
result Framework significantly outperforms existing IRL solutions and handles time-varying intentions.
This paper distills a complex travel mode choice model into simpler, interpretable models.
problem Lack of interpretability in complex machine learning models for travel behavior.
method Model distillation combined with market segmentation.
result Generated interpretable models that closely match the predictions of the original complex model.
Neural network learns to explore and predict actions in a simulated environment.
problem Replicate infants' ability to generate structured behaviors in unstructured environments.
method Curiosity-driven intrinsic motivation, adversarial learning, world model prediction.
result Self-supervised emergence of complex behaviors including object gathering.
RL agent learns to avoid market spoofing.
problem Avoiding subtle non-normative behavior in trading agents.
method Learned recognizer incorporated into RL agent's reward function.
result RL agent avoids spoofing while remaining profitable.
Managing a portfolio to a risk model can tilt the portfolio toward weaknesses of the model. As a result, the optimized portfolio acquires downside exposure to uncertainty in the model itself, what we call "second order risk." We propose a risk measure that accounts for this bias. Studies of real portfolios, in asset-by…
Agents buy and sell services. All services are of equal quality. Buyers choose sellers at random. Monetary and fiscal policies are imposed by a central bank and a central government. Credit is supplied by a commercial banking system. Propensities to buy, sell, and lend depend on account balances, interest rates, tax ra…
New method corrects state distribution mismatch for off-policy policy optimization.
problem Mismatch between behavior and evaluation policy state distributions.
method Off-policy policy gradient with state distribution correction.
result Significantly improved policy quality in simulations.
New method infers human sensorimotor costs from behavior.
problem Inferring human sensorimotor costs from observed behavior.
method Inverse optimal control with signal-dependent noise.
result Recovering costs and benefits in sensorimotor behavior.
Surprise describes a range of phenomena from unexpected events to behavioral responses. We propose a measure of surprise and use it for surprise-driven learning. Our surprise measure takes into account data likelihood as well as the degree of commitment to a belief via the entropy of the belief distribution. We find th…