Search Results (44)

Bayesian optimization (BO) is a widely used framework for optimizing expensive black-box functions. Most BO methods rely on Gaussian process (GP) surrogates, which perform well in continuous domains but encounter difficulties when decision variables include categorical or mixed discrete–continuous components. In particular, GP-based approaches typically require ad hoc numerical encodings of categorical variables that may fail to capture the structure of discrete decision spaces. In this work, we propose MNL-BO (Multinomial Logit Bayesian Optimization), a preference-based Bayesian optimization framework that replaces the GP surrogate with a multinomial logit (MNL) model trained from pairwise preference comparisons. The resulting surrogate provides a natural and interpretable representation of categorical alternatives while allowing continuous, discrete, and categorical variables to be handled within a unified optimization framework. The predictive utility estimates and uncertainty indicators generated by the MNL model are employed to formulate acquisition functions that reconcile exploration with exploitation. The proposed methodology is evaluated on three progressively complex optimization challenges: a purely categorical benchmark, a combinatorial Traveling Salesman problem, and a constrained mixed-variable engineering design problem concerning material selection in pressure vessel optimization. Multi-run tests provide consistent advantages over random search and exhibit stable convergence behavior across diverse random initializations. In addition to heuristic baselines such as local search and classical metaheuristics, we also compare against tree-based Bayesian optimization baselines inspired by the Sequential Model-based Algorithm Configuration (SMAC) framework. The results indicate that the proposed MNL-BO method achieves competitive performance under comparable evaluation budgets while providing an interpretable probabilistic surrogate for categorical decision spaces. These findings suggest that preference-based surrogate modeling provides a practical and flexible alternative for Bayesian optimization in categorical and mixed-variable optimization problems. Full article

Rapid growth in urban population, vehicle ownership, and spatial expansion places increasing pressure on urban transportation networks, necessitating a shift toward sustainable mobility solutions. Accordingly, this study examines the determinants of university students’ mode choice preferences for home-to-campus commuting in a small-scale city. The analysis incorporates socio-demographic factors, mobility resources, and travel attributes as potential influencers of mode choice. For modeling preferences, a Multinomial Logit (MNL) model was initially used to estimate deterministic effects, followed by a Mixed Multinomial Logit (MMNL) model to capture unobserved heterogeneity at the individual level. The results demonstrate that gender, vehicle ownership, and travel distance play statistically significant roles in mode choice. Crucially, the MMNL analysis reveals that while students’ sensitivity to travel time is relatively homogeneous, their sensitivity to travel cost exhibits significant unobserved heterogeneity. Moreover, the study reveals the potential for a modal shift toward sustainable options such as walking, cycling, and public transport. These findings offer valuable insights for promoting sustainable urban mobility and developing data-driven transport policies, specifically in alignment with the “Sustainable Cities and Communities” goal of the United Nations (UN) Sustainable Development Goals (SDGs). Full article

Parking management in mid-sized Latin American cities is often limited by weak enforcement, scarce off-street supply, and widespread irregular parking. This study uses a stated preference experiment to analyze parking choices among 227 drivers in Loja, Ecuador. Six choice tasks evaluated four alternatives—regulated on-street, private off-street, irregular parking, and leaving the vehicle at home—based on cost, walking distance, search time, availability, expected fines, and security. Multinomial logit (MNL) and mixed logit (ML) models were estimated, including income- and gender-based segmentations. Results show that cost (β = −0.332, p < 0.01) and walking distance (β = −0.0026, p < 0.001) are the primary determinants of formal parking choice. The willingness to pay to avoid 100 m of walking is USD 0.77 per 2-h period. Low-income users are 4.8 times more sensitive to cost. Mixed logit results reveal significant heterogeneity in preferences for cost, search time, and enforcement sensitivity. Policy simulations indicate that increasing enforcement (70% probability, USD 250 fine) reduces illegal parking demand by 93%, while lowering regulated tariffs to USD 0.50 raises its share by 4.2 percentage points. These findings support sustainable mobility policies by promoting efficient parking management, reducing illegal parking, and improving equitable access to urban space. Full article

The accurate measurement and optimization of spatial vitality inside commercial complexes has become crucial for sophisticated urban governance as urban growth moves from rapid expansion to quality-oriented stock augmentation. This research creates a multifaceted assessment methodology that incorporates systemic connectedness (transportation synergy), spatial performance (public activity and social efficacy), and spatial supply (human–land linkages and arrangement). We used a stratified purposive sample of 20 business complexes spread across eight districts in Guangzhou, a typical high-density megacity. In order to understand the underlying mechanisms of spatial vitality, we measured important indicators including the Polycentricity Index (α) and the Spatial Performance Index (β) using a mixed-methods approach that included K-means clustering, multinomial logit regression, and Structural Equation Modeling (SEM). Four important insights are shown by our findings. 1. The paradox of density and efficiency: The notion that high-density development inevitably ensures lively public space is called into question by the lack of a significant linear correlation between the Floor Area Ratio (FAR) and spatial performance (r = 0.32, p > 0.05), despite a core–periphery gradient in development intensity. 2. Structural Supply Demand Mismatch: Although overall spatial performance is strong (β = 0.81 ± 0.07), there is a notable shortfall in cultural and artistic venues, where young adults’ demand (0.27) is 145% greater than supply (0.11). 3. Polycentric Networking vs. Transport Polarization: While spatial structures show a networked polycentric pattern (mean α = 6.40), transportation synergy is affected by core–periphery polarization, which results in “vitality islands” in the periphery. 4. Dual-Path Driving Mechanisms: According to SEM results, cultural spaces have a considerable indirect impact (39.7% mediation) by boosting brand uniqueness and “cultural capital,” while composite plaza spaces have a strong direct effect on commercial performance (γ = 0.682). Based on these findings, we suggest distinct optimization strategies: aging projects need climate-responsive design interventions; growing areas should create family-oriented consumption ecosystems; and core districts should give priority to cultural “IP” integration. For the planning and revitalization of commercial land use in high-density global environments, this study offers a solid analytical framework and practical insights. Full article

Flood hazard mitigation programs increasingly rely on property buyouts and home elevation, yet participation remains sensitive to program design details that affect household constraints. This study estimates homeowner preferences for buyout and elevation program attributes using a stated-preference discrete-choice experiment administered to N = 1560 homeowners, in which each respondent completed up to 4 choice tasks with 3 alternatives (Buyout, Elevation, and Neither). Choices are modeled in a random-utility framework with a multinomial logit as the primary specification and a mixed logit as a robustness specification. Observed choices favor Buyout (51.2%) over Elevation (29.6%) and the status quo (19.2%). In the estimated utility model, higher buyout offers increase acceptance, longer payment delays significantly reduce acceptance, and longer time to vacate increases acceptance; the acquisition option feature also raises buyout utility. These timing effects imply economically meaningful offer-equivalent tradeoffs: at representative baselines, an additional month of payment delay requires approximately a 6.45 percentage-point increase in offer (as a share of home value) to maintain acceptance, while households would trade about 8.02 percentage points of offer to obtain one additional month to vacate. Heterogeneity results indicate lower baseline participation among low-income respondents and attenuated marginal benefits of longer vacate time among respondents reporting damage. Respondent-level cross-validation shows stable predictive performance and similar accuracy across MNL and mixed logit models. The results highlight that accelerating payments and offering flexible time to vacate can increase program uptake, and that complementary supports may be needed to reduce participation barriers for economically vulnerable households. Full article

Globally, the demand for beef and beef-related products has significantly escalated over the past decade. This study aimed to evaluate the factors influencing the market participation of smallholder beef cattle farmers in uMgungundlovu, South Africa. The study employed a cross-sectional research design, which followed a mixed-methods approach to collect data. Survey data were collected from smallholder cattle farmers from the uMgungundlovu District in KwaZulu-Natal using a semi-structured questionnaire. Purposive sampling was employed to select four local municipalities from the uMgungundlovu District out of a total of seven, whereas a simple random sampling was used to recruit farmers. The sampling was conducted using Microsoft Excel, whereby each farmer was allocated a random number, and then the required sample was generated from those numbers. To determine factors that influence farmers’ market choice, a multinomial logit regression model was used. A significant proportion of the farmers (43.1%) were aged between 51 and 70, followed by 35.5% aged 31 to 50. Just under half (48.2%) of farmers had received formal training in livestock production. This finding (p < 0.001) reinforces the central role of education in income determination. Better-educated individuals tend to earn more and diversify their income sources. This study underpinned that the livestock farming population is dominated by primarily middle-aged, male, semi-educated, and resource-poor individuals, and they rely significantly on traditional farming methods and government assistance. The multinomial logit regression revealed that farmers’ market choices are influenced by education level, extension service quality, access to quality bulls, and breeding knowledge significantly influenced farmers’ market choices. Specifically, secondary and tertiary education reduced the likelihood of participating in auction markets relative to informal markets, while limited breeding knowledge and poor extension services further constrained participation in formal channels. Full article

Soils are critical natural resources, yet their abiotic contributions to ecosystem services remain largely unexplored in valuation studies. This pilot study represents, to the best of our knowledge, the first attempt to assess the perceived value of geosystem services (GSs) from a consumer perspective. Using a discrete choice experiment with 200 respondents, we evaluated preferences for Rotella apples and Moscatello wine through mixed multinomial logit and latent class models. Results show that attributes related to soil use and soil control were consistently significant drivers of consumer utility (e.g., odds ratios of 9.38 and 5.78 for Moscatello wine and 8.46 and 5.56 for Rotella apples, respectively; p < 0.01). These attributes align more closely with the concept of a “geological fingerprint” than with existing geographical labeling schemes such as the Protected Designation of Origin. Price effects were statistically insignificant, indicating virtually no influence on choices. Both estimated models revealed preference heterogeneity and a substantial number of no-buy responses. This suggests both limited consumer familiarity with GS concepts and a limitation of our attribute descriptions, which likely failed to convey information needed for effective purchasing decisions. This study is exploratory and limited by its convenience sample, imperfect price specification, and inability to estimate willingness-to-pay measures. Nevertheless, it provides empirical support for introducing geological footprint labeling and highlights the need for improved consumer information, policy tools, and public campaigns to promote recognition and sustainable management of geodiversity in agriculture. Full article

The increasing environmental concerns of plastic waste have encouraged more interest in environmentally friendly packaging, but consumer willingness to pay (WTP) for green alternatives in emerging markets such as Saudi Arabia is not fully explored. This research explores the relationship between awareness of sustainability and price sensitivity in determining WTP for green packaging in the Saudi retail market. The study utilizing a mixed method included both a Contingent Valuation Method (CVM) and a Discrete Choice Modeling (DCM). In it, data was gathered and analyzed using a sample of 424 urban consumers in Saudi Arabia’s major cities. The findings of OLS regression indicated awareness of sustainability had a significant, positive effect on WTP, whereas price sensitivity had a negative effect. There was a marginal interaction effect indicating that awareness could overcome price aversion. Logistic regression supported awareness as a dominant factor in binary product choice, although price sensitivity was not significant in the said model. The multinomial logit model also showed that the type of package, environmental labels (more so the “100% recyclable” type), and price had significant effects on consumer preferences. These results indicate that there is acceptance of sustainable packaging by consumers in Saudi Arabia if the product is communicated effectively and priced competitively. Full article

This study identified the main factors affecting car selection decisions through discrete choice experiments based on a large dataset collected in four European countries in 2023 using stated choice questionnaires. The choice set includes six current and popular car powertrains with factors related to vehicle features, user characteristics, and specific geographical contexts, which can influence the adoption of vehicles with electrified powertrains. An easily applicable multinomial logit model was first proposed to explore the effects of selected attributes and the model’s ability to reproduce user preferences with different incentive policies, geographical contexts, and energy prices. A mixed logit model and a segmented multinomial logit model were introduced to consider the sample’s heterogeneity. The first captures the preference dispersion among respondents related to incentives and operational costs. The second, which specifically classifies users based on car market segments, showed a greater variation in factors related to the purchase cost and battery range. The models estimate the weight of nine factors, offering support for targeted policy recommendations. Cost-related factors confirm their relevance in choices, and the analysis shows that users who want to enhance their vehicle range by 1 km are willing to pay approximately EUR 80. Full article

School trips affect different aspects, such as air pollution and urban traffic, and of personal wellbeing, such as students’ physical and mental health. The increasing concern about environmental sustainability has prompted a reevaluation of daily activities, including school transportation. While different factors that affect students’ school trips have been investigated in the literature, the effect of the built environment has been evaluated only sporadically in previous studies. To fulfil this knowledge gap, this study aims to investigate the effect of the built environment on students’ school trips by adapting and extending the well-known Neighborhood Environment Walkability Scale (NEWS) questionnaire. The questionnaire survey was conducted with parents from 36 schools in Yazd, Iran, providing a sample of 1688 students aged 7–18 years. The items from the NEWS questionnaire were placed in nine factors by performing factor analysis. The Multinomial Logit Regression model was applied to check the predictive power of these nine factors. It was found that the variables of land use mix-diversity, land use mix-access, crime, age, gender, household income and car ownership had a significant effect on students’ school trips. The more easily students have access to different places, the less they use public services and cars compared with the active travel mode. The use of public services and cars increases with the increase in crime rate along the route to school. The findings indicate that built environment features may impact students’ shift from traditional transportation modes to active alternatives, such as walking and cycling, contributing to the attainment of broader sustainability objectives. Full article

Human-driven vehicles (HDVs) will share the road with connected autonomous vehicles (CAVs) in the near future. Accordingly, the investigation of the interactive behavior of HDV drivers toward CAVs is becoming critical. In this study, a questionnaire survey was first conducted. The heterogenous clusters of HDV drivers were revealed through the latent profile analysis based on the collected dataset, with the focus on their trust and familiarity with CAVs, their attitudes towards sharing the road with CAVs, and their risk perception and perceived behavior control when they faced the CAVs. Subsequently, the correlation between the respective latent cluster and several socio-demographic factors was understood based on the multinomial logistic regression model, and the choice behavior of each cluster in different interactive driving scenarios was revealed. Three vital findings were reported. (1) Three profile clusters of HDV drivers (i.e., negative individuals, neutral individuals, and positive individuals) were revealed. (2) The drivers of a low/middle income and with a long driving experience were more likely to be negative individuals, whereas the CAV experience can make drivers feel positive towards CAVs. (3) Negative individuals might give up on changing lanes when a CAV platoon driving was noticed in the target lanes; in addition, they might raise more rigorous requirements for vehicle spacing in the lane-changing process when finding CAVs driving in the target lanes. To be specific, negative and neutral individuals preferred driving in front of the CAV platoons. The findings can provide references for developing effective management measures or CAV control strategies for transportation systems. Full article

We explore whether there are value preferences of creative workers in addition to tolerance and how these value preferences vary among different occupation categories and countries. We use a dataset of 1968 and 1076 observations in China and the U.S., respectively, from the World Values Survey dataset (2017–2020, wave 7) (WVS 7), with a Structure Equation Modelling (SEM) and Multinomial Logit Model (MLM) at the micro level. The findings reveal that (1) the Chinese sample is more likely to have a balanced preference of tolerance towards migrants, religions, and homosexuality, while the American sample’s preference of tolerance is much more likely to be interpreted as accepting homosexuality only; (2) the American sample also shows preferences towards responsibility, technology, work style, and political actions, while a preference for happiness and political actions is identified in the Chinese sample; and (3) with a higher level of creativity, the difference regarding understanding of tolerance is more likely to be highlighted between China and the U.S. This study provides a quite unconventional perspective for understanding the composition of preferences and, to a certain extent, reconciles the inconsistency between the theoretical advocacy of building up a selected milieu and the reality of creative workers’ blended value mix. Full article

A generalized multinomial logit (G-MNL) model is proposed to alleviate the four challenges inherent to the conditional logit model, including (1) simultaneous unidentifiability, (2) the immediacy of decision-making, (3) the homogeneity of preferences in unobservable variables, and (4) the independence of irrelevant alternatives. However, the G-MNL model has some restrictions that are caused by the assumed logit scale of the lognormal distribution used in the G-MNL model. We propose a mixed logit with integrated Pareto-distributed scale (MIXL-iPS) model to address the restriction of the G-MNL model by introducing a logit scale in accordance with the Pareto distribution type I with an expected value of 1. We have clarified the mathematical properties and examined the distributional properties of the novel MIXL-iPS model. The results suggest that the MIXL-iPS model is a model in which the instability in the estimation of the G-MNL model is modified. Moreover, the apparent preference parameter was confirmed to have a skewed distribution in general in the MIXL-iPS model. In addition, we confirm that in the MIXL-iPS model, bounded rationality is reasonably well represented, as many individuals have below-average choice consistency. Full article

Amman, the capital of Jordan, has experienced significant traffic congestion due to the rise in private vehicle ownership and limited public transportation services. A Stated Preference (SP) survey was conducted to determine public transportation users’ willingness to use the Bus Rapid Transit (BRT) service. Another survey assessed the demand for an on-demand transit bus service with flexible and moderate costs, particularly for individuals far from the main BRT stations who need to reach them. Two models, Multinomial Logit (MNL) and Mixed Logit (ML), were utilized to understand user preferences for work-related trips. The study findings indicate that the cost of the trip and the waiting time are the two primary factors influencing public transport users’ choices. Furthermore, sociodemographic factors, such as age, income, household size, and current status, were found to have a significant impact. The results reveal that approximately 71% of participants would utilize an integrated public transportation system comprising BRT and on-demand services. The findings underscore the potential benefits of an integrated public transport system in addressing Amman’s traffic congestion. By combining BRT and on-demand services, the city can offer residents comfortable, affordable, and efficient transportation options, thus effectively mitigating congestion. Full article

This paper investigated factors influencing injury severity of crashes involving median traffic barriers, including the impact of barrier characteristics and their geometric features in Wyoming. Combining field data of inventoried median barriers with crash data on Wyoming interstates highways, a random parameters multinomial logit (mixed logit) model of injury severity was estimated. This methodological approach allowed for the possibility of estimated model parameters to vary randomly across crash observations to account for heterogeneity with respect to driver characteristics, roadway attributes, and vehicle characteristics. The estimation results indicated concrete barriers installed on front side-slopes and box beam barriers were associated with severe injury crashes. It was also found that median barrier crashes involving sports utility vehicles, pickups, and improperly restraint vehicle occupants are complex and vary significantly across observations. Other statistically significant variables found to increase the likelihood of severe injury crashes were rural interstate roads, concrete barriers installed on a front side-slope, box beam barriers with lateral offset less than 2 feet, and rollover crashes. These parameters were fixed across observations. The findings of this research point to the need to further investigate the impacts of sport utility vehicles, pickups, and rollover crashes on median barrier crash injury severity. Full article