To make effective decisions, it is important to have a thorough understanding of the causal relationships among actions, environments, and outcomes. This review aims to surface three crucial aspects of decision-making through a causal lens: 1) the discovery of causal relationships through causal structure learning, 2) understanding the impacts of these relationships through causal effect learning, and 3) applying the knowledge gained from the first two aspects to support decision making via causal policy learning. Moreover, we identify challenges that hinder the broader utilization of causal decision-making and discuss recent advances in overcoming these challenges. Finally, we provide future research directions to address these challenges and to further enhance the implementation of causal decision-making in practice, with real-world applications illustrated based on the proposed causal decision-making. We aim to offer a comprehensive methodology and practical implementation framework by consolidating various methods in this area into a Python-based collection. URL: https://causaldm.github.io/Causal-Decision-Making.
The recent democratization of personal fabrication has significantly advanced the maker movement and reshaped applied research in HCI and beyond. However, this growth has also raised increasing sustainability concerns, as material waste is an inevitable byproduct of making and rapid prototyping. In this work, we examine the sustainability landscape within the modern maker community, focusing on grassroots makerspaces and maker-oriented research labs through in-depth interviews with diverse stakeholders involved in making and managing making-related activities. Our findings highlight four key themes: the various types of "waste" generated through the making process, the strategies (or lack thereof) for managing this waste, the motivations driving (un)sustainable practices, and the challenges faced. We synthesize these insights into design considerations and takeaways for technical HCI researchers and the broader community, focusing on future tools, infrastructures, and educational approaches to foster sustainable making.
Challenges, such as a lack of information for emergency decision-making, time pressure, and limited knowledge of experts acting as decision-makers (DMs), can result in the generation of poor or inconsistent indirect information regarding DMs' preferences. Simultaneously, the empathic relationship represents a tangible social connection within the context of actual emergency decision-making, with the structure of the empathic network being a significant factor influencing the outcomes of the decision-making process. To deduce the empathic network underpinning the decision behaviors of DMs from incomplete and inconsistent preference information, we introduce an empathic network learning methodology rooted in the concept of robust ordinal regression via preference disaggregation. Firstly, we complete incomplete fuzzy judgment matrices including holistic preference information given in terms of decision examples on some reference alternatives, independently by each DM, and we calculate the intrinsic utilities of DMs. Secondly, we establish constraints for empathic network learning models based on empathic preference information and information about relations between some reference nod
The growing integration of robots in shared environments - such as warehouses, shopping centres, and hospitals - demands a deep understanding of the underlying dynamics and human behaviours, including how, when, and where individuals engage in various activities and interactions. This knowledge goes beyond simple correlation studies and requires a more comprehensive causal analysis. By leveraging causal inference to model cause-and-effect relationships, we can better anticipate critical environmental factors and enable autonomous robots to plan and execute tasks more effectively. To this end, we propose a novel causality-based decision-making framework that reasons over a learned causal model to assist the robot in deciding when and how to complete a given task. In the examined use case - i.e., a warehouse shared with people - we exploit the causal model to estimate battery usage and human obstructions as factors influencing the robot's task execution. This reasoning framework supports the robot in making informed decisions about task timing and strategy. To achieve this, we developed also PeopleFlow, a new Gazebo-based simulator designed to model context-sensitive human-robot spat
This paper introduces SOLID (Synergizing Optimization and Large Language Models for Intelligent Decision-Making), a novel framework that integrates mathematical optimization with the contextual capabilities of large language models (LLMs). SOLID facilitates iterative collaboration between optimization and LLMs agents through dual prices and deviation penalties. This interaction improves the quality of the decisions while maintaining modularity and data privacy. The framework retains theoretical convergence guarantees under convexity assumptions, providing insight into the design of LLMs prompt. To evaluate SOLID, we applied it to a stock portfolio investment case with historical prices and financial news as inputs. Empirical results demonstrate convergence under various scenarios and indicate improved annualized returns compared to a baseline optimizer-only method, validating the synergy of the two agents. SOLID offers a promising framework for advancing automated and intelligent decision-making across diverse domains.
Many HCIxfabrication systems are compelling as prototypes but remain difficult to reuse, extend, or transfer beyond their original publication. A common explanation is that adoption simply takes time. We argue that the issue is more fundamental. The knowledge needed to make fabrication systems transferable, namely how they behave across different materials, machines, and users, usually does not exist at the time of publication because the work required to generate this knowledge is rarely incentivized or rewarded. Drawing on engineering epistemology and prior debates in systems-oriented HCI, we reframe engineering maturity as epistemic work: sustained engineering effort that produces knowledge which prototyping alone cannot reveal. We propose six dimensions, Fab-ilities, as a vocabulary to describe what aspects of fabrication artifacts have become established and what knowledge remains tacit: (1) buildability, (2) executability, (3) reliability, (4) maintainability, (5) transferability, and (6) scalability. We describe five of our own projects (JigFab, StoryStick++, Silicone Devices, LamiFold, and PaperPulse), where varied attempts at dissemination, such as commercialization, spin-
Reusing and making sense of other scientists' computational notebooks. However, making sense of existing notebooks is a struggle, as these reference notebooks are often exploratory, have messy structures, include multiple alternatives, and have little explanation. To help mitigate these issues, we developed a catalog of cognitive tasks associated with the sensemaking process. Utilizing this catalog, we introduce Porpoise: an interactive overlay on computational notebooks. Porpoise integrates computational notebook features with digital design, grouping cells into labeled sections that can be expanded, collapsed, or annotated for improved sensemaking. We investigated data scientists' needs with unfamiliar computational notebooks and investigated the impact of Porpoise adaptations on their comprehension process. Our counterbalanced study with 24 data scientists found Porpoise enhanced code comprehension, making the experience more akin to reading a book, with one participant describing it as It's really like reading a book.
Career decision-making is a socio-technical problem: individuals exercise bounded agency while navigating labor market institutions, organizational incentive structures, and information asymmetries that shape feasible trajectories. Existing frameworks optimize along single dimensions - financial returns, work-life balance, or mission alignment - without explicit models for inter-dimensional tradeoffs or temporal dynamics. We propose The Three Axes of Success, a normative decision framework decomposing career trajectories into Wealth (career capital accumulation and economic optionality), Autonomy (control over task selection, temporal allocation, and strategic direction), and Meaning (counterfactual social impact scaled by problem importance and personal replaceability). We formalize coupling dynamics between axes: the adjacent possible mechanism by which skill frontiers enable mission discovery, creating nonlinear Wealth -> Meaning transitions; autonomy prerequisites where insufficient career capital triggers control traps; and dual-career household constraints that yield Pareto-suboptimal Nash equilibria under independent optimization. We operationalize each axis through measu
The paper focuses on composite multistage decision making problems which are targeted to design a route/trajectory from an initial decision situation (origin) to goal (destination) decision situation(s). Automobile routing problem is considered as a basic physical metaphor. The problems are based on a discrete (combinatorial) operations/states design/solving space (e.g., digraph). The described types of discrete decision making problems can be considered as intelligent design of a route (trajectory, strategy) and can be used in many domains: (a) education (planning of student educational trajectory), (b) medicine (medical treatment), (c) economics (trajectory of start-up development). Several types of the route decision making problems are described: (i) basic route decision making, (ii) multi-goal route decision making, (iii) multi-route decision making, (iv) multi-route decision making with route/trajectory change(s), (v) composite multi-route decision making (solution is a composition of several routes/trajectories at several corresponding domains), and (vi) composite multi-route decision making with coordinated routes/trajectories. In addition, problems of modeling and building
Generative models have fundamentally reshaped the landscape of decision-making, reframing the problem from pure scalar reward maximization to high-fidelity trajectory generation and distribution matching. This paradigm shift addresses intrinsic limitations in classical Reinforcement Learning (RL), particularly the limited expressivity of standard unimodal policy distributions in capturing complex, multi-modal behaviors embedded in diverse datasets. However, current literature often treats these models as isolated algorithmic improvements, rarely synthesizing them into a single comprehensive framework. This survey proposes a principled taxonomy grounding generative decision-making within the probabilistic framework of Control as Inference. By performing a variational factorization of the trajectory posterior, we conceptualize four distinct functional roles: Controllers for amortized policy inference, Modelers for dynamics priors, Optimizers for iterative trajectory refinement, and Evaluators for trajectory guidance and value assessment. Unlike existing architecture-centric reviews, this function-centric framework allows us to critically analyze representative generative families acr
Knowledge tracing (KT) models are a crucial basis for pedagogical decision-making, namely which task to select next for a learner and when to stop teaching a particular skill. Given the high stakes of pedagogical decisions, KT models are typically required to be interpretable, in the sense that they should implement an explicit model of human learning and provide explicit estimates of learners' abilities. However, to our knowledge, no study to date has investigated whether the interpretability of KT models actually helps human teachers to make teaching decisions. We address this gap. First, we perform a simulation study to show that, indeed, decisions based on interpretable KT models achieve mastery faster compared to decisions based on a non-interpretable model. Second, we repeat the study but ask $N=12$ human teachers to make the teaching decisions based on the information provided by KT models. As expected, teachers rate interpretable KT models higher in terms of usability and trustworthiness. However, the number of tasks needed until mastery hardly differs between KT models. This suggests that the relationship between model interpretability and teacher decisions is not straight
This paper is on decision making of autonomous vehicles for handling roundabouts. The round intersection is introduced first followed by the Markov Decision Processes (MDP), the Partially Observable Markov Decision Processes (POMDP) and the Object Oriented Partially Observable Markov Decision Process (OOPOMDP). The Partially Observable Monte-Carlo Planning algorihtm (POMCP) algorithm is introduced and OOPOMDP is applied to decision making for autonomous vehicles in round intersections. Decision making is formulated as a POMDP problem and the penalty function is formulated and set followed by improvement of decision making with policy prediction. The augmented objective state and policy based state transition is introduced simulations are used to demonstrate the effectiveness of the proposed method.
A novel high-frequency market-making approach in discrete time is proposed that admits closed-form solutions. By taking advantage of demand functions that are linear in the quoted bid and ask spreads with random coefficients, we model the variability of the partial filling of limit orders posted in a limit order book (LOB). As a result, we uncover new patterns as to how the demand's randomness affects the optimal placement strategy. We also allow the price process to follow general dynamics without any Brownian or martingale assumption as is commonly adopted in the literature. The most important feature of our optimal placement strategy is that it can react or adapt to the behavior of market orders online. Using LOB data, we train our model and reproduce the anticipated final profit and loss of the optimal strategy on a given testing date using the actual flow of orders in the LOB. Our adaptive optimal strategies outperform the non-adaptive strategy and those that quote limit orders at a fixed distance from the midprice.
Most decision-making models, including the pairwise comparison method, assume the decision-makers honesty. However, it is easy to imagine a situation where a decision-maker tries to manipulate the ranking results. This paper presents three simple manipulation methods in the pairwise comparison method. We then try to detect these methods using appropriately constructed neural networks. Experimental results accompany the proposed solutions on the generated data, showing a considerable manipulation detection level.
We review economic research regarding the decision making processes of individuals in economics, with a particular focus on papers which tried analyzing factors that affect decision making with the evolution of the history of economic thought. The factors that are discussed here are psychological, emotional, cognitive systems, and social norms. Apart from analyzing these factors, it deals with the reasons behind the limitations of rational decision-making theory in individual decision making and the need for a behavioral theory of decision making. In this regard, it has also reviewed the role of situated learning in the decision-making process.
Machine learning-based techniques open up many opportunities and improvements to derive deeper and more practical insights from data that can help businesses make informed decisions. However, the majority of these techniques focus on the conventional closed-set scenario, in which the label spaces for the training and test sets are identical. Open set recognition (OSR) aims to bring classification tasks in a situation that is more like reality, which focuses on classifying the known classes as well as handling unknown classes effectively. In such an open-set problem the gathered samples in the training set cannot encompass all the classes and the system needs to identify unknown samples at test time. On the other hand, building an accurate and comprehensive model in a real dynamic environment presents a number of obstacles, because it is prohibitively expensive to train for every possible example of unknown items, and the model may fail when tested in testbeds. This study provides an algorithm exploring a new representation of feature space to improve classification in OSR tasks. The efficacy and efficiency of business processes and decision-making can be improved by integrating OSR
We propose a macroscopic market making model à la Avellaneda-Stoikov, using continuous processes for orders instead of discrete point processes. The model intends to bridge the gap between market making and optimal execution problems, while shedding light on the influence of order flows on the optimal strategies. We demonstrate our model through three problems. The study provides a comprehensive analysis from Markovian to non-Markovian noises and from linear to non-linear intensity functions, encompassing both bounded and unbounded coefficients. Mathematically, the contribution lies in the existence and uniqueness of the optimal control, guaranteed by the well-posedness of the strong solution to the Hamilton-Jacobi-Bellman equation and the (non-)Lipschitz forward-backward stochastic differential equation. Finally, the model's applications to price impact and optimal execution are discussed.
We study individual decision-making behavioral on generic view. Using a formal mathematical model, we investigate the action mechanism of decision behavioral under subjective perception changing of task attributes. Our model is built on work in two kinds classical behavioral decision making theory: "prospect theory (PT)" and "image theory (IT)". We consider subjective attributes preference of decision maker under the whole decision process. Strategies collection and selection mechanism are induced according the description of multi-attributes decision making. A novel behavioral decision-making framework named "ladder theory (LT)" is proposed. By real four cases comparing, the results shows that the LT have better explanation and prediction ability then PT and IT under some decision situations. Furthermore, we use our model to shed light on that the LT theory can cover PT and IT ideally. It is the enrichment and development for classical behavioral decision theory and, it has positive theoretical value and instructive significance for explaining plenty of real decision-making phenomena. It may facilitate our understanding of how individual decision-making performed actually.
In the field of Sequential Decision Making (SDM), two paradigms have historically vied for supremacy: Automated Planning (AP) and Reinforcement Learning (RL). In the spirit of reconciliation, this article reviews AP, RL and hybrid methods (e.g., novel learn to plan techniques) for solving Sequential Decision Processes (SDPs), focusing on their knowledge representation: symbolic, subsymbolic, or a combination. Additionally, it also covers methods for learning the SDP structure. Finally, we compare the advantages and drawbacks of the existing methods and conclude that neurosymbolic AI poses a promising approach for SDM, since it combines AP and RL with a hybrid knowledge representation.
We model human decision-making behaviors in a risk-taking task using inverse reinforcement learning (IRL) for the purposes of understanding real human decision making under risk. To the best of our knowledge, this is the first work applying IRL to reveal the implicit reward function in human risk-taking decision making and to interpret risk-prone and risk-averse decision-making policies. We hypothesize that the state history (e.g. rewards and decisions in previous trials) are related to the human reward function, which leads to risk-averse and risk-prone decisions. We design features that reflect these factors in the reward function of IRL and learn the corresponding weight that is interpretable as the importance of features. The results confirm the sub-optimal risk-related decisions of human-driven by the personalized reward function. In particular, the risk-prone person tends to decide based on the current pump number, while the risk-averse person relies on burst information from the previous trial and the average end status. Our results demonstrate that IRL is an effective tool to model human decision-making behavior, as well as to help interpret the human psychological process