Productivity Costs Research Articles

Productivity loss due to acute COVID-19 and post COVID-19 condition in the Northern Netherlands

Abstract Introduction The COVID-19 pandemic caused significant socioeconomic and health shocks worldwide. Yet, research is still scarce on how acute COVID-19 and post COVID-19 condition (PCC) have impacted workers productivity in terms of absenteeism, presenteeism and reduced unpaid work. This study examines the effect of acute COVID-19 and PCC on Dutch workers’ loss of work productivity in standardized hourly costs compared to those with neither disease. Methods This study included data from 31 waves (March 2020 - October 2022) of the Lifelines COVID-19 cohort, a populational cohort from the Netherlands. Productivity was measured in 7 waves in terms of absenteeism, presenteeism, and loss of unpaid work using the Medical Technology Assessment Productivity Costs Questionnaire. We selected workers aged 18 to 64 in the first wave (n = 10,950). Using administrative data, average hourly costs of productivity were calculated as 38.67€ for absenteeism and presenteeism and 15.94€ for unpaid work. The friction cost method was used. To compare group differences, a Kruskal-Wallis rank sum test with Holms-Bonferroni p-value adjustment was performed. Results In total, 33.4% of participants had acute COVID-19, 5.7% had PCC, and 60.9% had neither disease. The mean total combined productivity loss per person of those with PCC was 7,118€, compared to 3,410€ for those with acute COVID-19, and 3,076€ for those with neither. When comparing groups, significant differences in costs were found for all aspects of productivity, except for unpaid work loss between acute COVID-19 and those with neither disease. Discussion Although the number of people with acute COVID-19 represents a large societal cost in terms of accumulated loss, those with PCC incurred on average twice as much productivity losses per person across all domains. This study highlights the high costs associated with PCC, which continues to chronically burden workers. Policies should be aimed at lessening this burden. Key messages • Post COVID-19 condition is associated with significantly higher average productivity costs per person than acute COVID-19, which highlights the individual burden of this chronic disease. • Acute COVID-19, despite relatively lower average productivity costs, represents a large societal cost in terms of accumulated loss.

Critical factors to adopt sustainable agrifood supply chain management in developing countries: The case of Ethiopian coffee industry

AbstractGlobal agrifood supply chains are under increasing pressure to address sustainability issues due to growing concerns. However, numerous organizations within the agrifood industry are struggling to incorporate sustainable supply chain management practices and address the concerns. Therefore, this research is designed to identify the key critical factors, such as drivers, enablers, and barriers to adopting sustainable practices. This study considers the Ethiopian coffee industry, which is an important sector not only for the Ethiopian economy but also for the global agrifood supply chain. To accomplish the objectives of this study, we applied a systematic literature review and empirical survey. A systematic literature review was conducted to identify critical factors for adopting sustainability in agrifood supply chains. An empirical survey was then undertaken in the Ethiopian coffee industry to rank the key critical factors. Hence, the study has revealed that economic and productivity improvement, cost effectiveness and improvement in the overall performance, and difficulty in mindset and cultural changes as the key critical factors that determine the adoption of sustainability initiatives from the perspectives of the Ethiopian coffee supply chain. The findings can be used as input by government regulatory bodies and policymakers to craft strategies and policies to adopt sustainability initiatives and ensure sustainable development. Furthermore, the research is expected to contribute to the existing literature by bringing in the perspective of suppliers in developing countries.

Impact of Skidding and Slope on Grapple Skidder Productivity and Costs: A Monte Carlo Simulation in Eucalyptus Plantations

Background: In the context of mechanized timber harvesting, alterations in technical parameters, such as skidding distance and terrain slope, have the potential to influence the productivity and production costs associated with the self-propelled grapple skidder. Furthermore, these variables are inherently uncertain, which could potentially cause forest managers to make inaccurate decisions. The objective was to analyze whether four skidding distances and two slope classes influence the productivity and production costs of the grapple skidder in Eucalyptus planted forests from a stochastic perspective using the Monte Carlo method. Methods: Productivity was estimated using the time study protocol. To calculate the cost per scheduled hour of the grapple skidder, both fixed and variable costs were considered, and subsequently, the production cost was determined. Results: The mean productivity of the grapple skidder on flat slopes was 114.35 m3 h−1, while on wavy to strong wavy slopes it was 80.43 m3 h−1. In flat slopes, considering all skid distance ranges, the mean production cost was 0.82 USD m−3, while in wavy to strong wavy slopes it was 1.48 USD m−3. The mean values for operator labor costs and fuel account for 58.1% of the cost per scheduled hour of the grapple skidder. Conclusions: The mean productivity of the grapple skidder in Eucalyptus planted forests decreased with increasing skidding distance in both slope classes but was 29.7% lower on wavy to strong wavy slopes compared to flat slopes. The mean production cost of the grapple skidder during timber skidding on flat slopes is 80.0% lower than on wavy to strong wavy slopes. For future investigations, the impact of other slope classes, skid distances, and silvicultural aspects on productivity and production costs can be considered from a stochastic perspective using the Monte Carlo method.

The Annual Economic Burden of Uterine Fibroids in the United States (2010 Versus 2022): A Comparative Cost-Analysis.

In 2010, the estimated annual cost of uterine fibroids in the United States ranged from 5.9 to 34.4billion USD. In the past decade, more uterine-sparing and fertility preserving interventions have become available to treat symptomatic fibroids. This comparative cost-analysis aims to evaluate change in societal costs of uterine fibroids in the US between 2010 and 2022 given changing fibroid and obstetric management, population growth, and inflation. A systematic review was conducted to update uterine fibroid, treatment, and obstetric complication prevalence, direct costs of medical and surgical interventions, indirect productivity costs, and obstetric costs attributable to fibroids in 2022. A comparative cost-analysis with paired t-tests was performed using baseline data published in 2010. Percent (%) changes between 2010 and 2022 were reported. NIH research funding for fibroids and other common diseases was compared. All costs were converted to 2023 USD. The number of US women with uterine fibroids increased by 10.6% from 2010 to 2022. Over this period, the economic burden of uterine fibroids increased up to 41.4billion USD compared to 34.4billion USD in 2010. Overall costs increased to 42.2billion USD after incorporating new costs associated with MRgFUS and infertility. Direct costs of medical management decreased while costs of surgical interventions increased as a result of evolving treatment-seeking behavior. Lost work costs continue to account for the largest proportion of the economic burden for fibroids. Cesarean section delivery remains the largest contributor (average 80.0%) to indirect obstetrical costs. Despite the rise in the number of individuals affected by uterine fibroids and its sizable annual cost to society, uterine fibroids research continues to be underfunded.

Cost of Illness Studiesin clinical depression Using Discounting Methods: A Comprehensive Analysis

Abstract:This research delves into the intricate domain of Cost of Illness (COI) studies, also known as Burden of Disease (BOD), with a specific focus on depressive disorders. Employing a bottom-up approach, the study meticulously scrutinizes the economic implications of depression at various levels, emphasizing direct and indirect costs. The analysis integrates a detailed exploration of diverse discounting methods, including Net Present Value (NPV) and Discounted Cash Flow (DCF), with a particular emphasis on the Indian context to comprehend unique socio-economic factors.Methodologically, the study systematically reviews scientific literature over the past decade, utilizing databases such as Web of Science and Google Scholar. The inclusion criteria prioritize patient-based studies related to the cost of illness associated with depression. The research adopts a comprehensive approach, considering various methodologies and discounting techniques to enhance the understanding of economic implications.The comparative analysis of the total cost of illness across diverse countries unravels significant variations, highlighting the intricate nature of healthcare expenditures and economic structures. Specific breakdowns for each country consider factors suchas currency exchange rates, inflation, and Purchasing Power Parity (PPP) adjustments, shedding light on the complexities involved.The study across five countries highlights significant variations in depression-related costs. Direct medical costs have a mean of $42,668 (SD=16,940) with a high t-statistic of 27.83 (p-value 0.001), emphasizing substantial differences. Direct non-medicalcosts average $27,171 (SD=13,220) with a t-statistic of 14.07 (p-value 0.001), indicating a notable economic burden beyond medical expenses. Indirect costs related to depression stand at a mean of $63,816 (SD=25,230), with a t-statistic of 35.30 (p-value 0.001), highlighting significant impacts on productivity and societal costs. The total cost of illness, encompassing both direct and indirect costs, averages $113,590 (SD=43,990), with a t-statistic of 49.49 (p-value 0.001), reflecting the extensive economic implications of depression across these diverse nations.In conclusion, this comprehensive analysis contributes depth to our understanding of the economic impact of depressive disorders, providing valuable insights for policymakers, healthcare providers, and researchers. The research underscores the multifacetednature of the economic burden of depression, emphasizing variations across countries and advocating for comprehensive, context-specific approaches in assessing and addressing global implications. Acknowledging challenges with discounting methods, the paper identifies opportunities for refining methodologies and improving economic evaluations in the future, emphasizing the importance of nuanced insights for effective policymaking and healthcare strategies on a global scale.

Determinants of Financial Viability of Forest Concession in Brazilian Amazon

This study aimed to assess the financial viability of forest concessions in the state of Pará, Brazil. Two Forest Management Units (FMUs) were analyzed: FMU-2, located in Saracá-Taquera National Forest, and FMU-3, located in Caxiuanã National Forest. Financial indicators were evaluated under different timber productivity scenarios (20 m3/ha and 25.8 m3/ha). At a logging intensity of 20 m3/ha, FMU-2 was not financially viable. However, both FMUs were financially viable at 25.8 m3/ha. Sensitivity analysis demonstrated that FMU-2 requires a logging intensity of over 22 m3/ha and a sawmill yield efficiency of at least 45%. The ideal cost for sawn wood would be USD 226.53/m3, with royalties of USD 16.00/m3. FMU-3 consistently demonstrated positive financial results, despite fluctuations in production costs. The financial viability of investing in forest concessions in state of Pará depends largely on forest productivity, sawmill yield, royalties, and sawn wood costs.

Productivity costs of the green energy transition in Africa

AbstractTransitioning to renewable energy generates tangible benefits in terms of the environment and emissions of greenhouse gases. However, the economic productivity costs of switching to clean energy cannot be overlooked, in addition to the large resource requirements, potential disruption in energy systems, risks of job losses, and emergence of new inequalities. Therefore, it is crucial to identify and quantify synergies and trade‐offs. This paper investigates the productivity cost of abandoning the use of fossil fuels in African countries, using econometric techniques applied to panel data, including the fully modified ordinary least square. The paper finds that, while renewable energy supply is beneficial to increase total factor productivity, in general, a shift toward a higher share of renewables in the power mix is not without productivity cost on the economy. The analysis accounts for other sources of productivity, such as human capital and the diffusion of embodied technology imported from abroad into local markets. The data also reveal that the energy transition could have heterogeneous effects depending on the regions' and countries' characteristics and stages of transition.

Cost-effectiveness of treatment sequences for BRAF-mutant advanced melanoma in the Netherlands using a health economic model

BackgroundThis study aims to evaluate the cost-effectiveness of treatment sequences for patients with advanced melanoma with a BRAF mutation in the Netherlands from a societal perspective. MethodsA semi-Markov model with a life-time horizon has been used to evaluate cost-effectiveness of 21 treatment sequences. Real-world data from the Dutch Melanoma Treatment Registry (DMTR) were used to estimate time to progression, next treatment and death. Utilities by health state as well as hospital costs, health care costs outside the hospital, patient and family costs and productivity costs were also derived from the DMTR. Drug costs were estimated based on the recommended dose and duration of treatment. Incremental cost-effectiveness ratios (ICERs) were presented as incremental costs per QALY gained. ResultsHealth benefits of treatment sequences consisting of targeted therapies and immunotherapies vary between 2.3 and 5.8 QALYs gained per patient when compared to chemotherapy. The increase in costs varies between €112,000 and €383,000. The efficiency frontier consists of nivolumab in the first line followed by ipilimumab in the second line (ICERs of €42,000/QALY and €44,000/QALY), nivolumab in the first line followed by encorafenib plus binimetinib in the second line (ICERs of €71,000/QALY and €68,000/QALY) and nivolumab plus ipilimumab in the first line followed by encorafenib plus binimetinib in the second line (ICERs of €74,000/QALY and €76,000/QALY). The first treatment given within a sequence as well as assumptions regarding treatment duration have a substantial impact on cost-effectiveness outcomes. ConclusionThe ICERs can be considered cost-effective at different cost-effectiveness thresholds.

Matched Comparison Examining the Effect of Obesity on Clinical, Economic, and Humanistic Outcomes in Patients with BipolarI Disorder.

BipolarI disorder (BD-I) is associated with an increased risk of obesity, but few studies have evaluated the real-world clinical, humanistic, and economic effects associated with obesity in people with BD-I. This was a retrospective, cross-sectional analysis of responses to the 2016 and 2020 National Health and Wellness surveys. Respondents (18-64years) with a self-reported physician diagnosis of BD-I were matched to controls without BD-I based on demographic and health characteristics. Respondents were categorized by body mass index as underweight/normal weight (< 25kg/m2), overweight (25 to < 30kg/m2), or obese (≥ 30kg/m2). Multivariable regression models were used to compare obesity-related comorbidities, healthcare resource utilization (HCRU), health-related quality of life (HRQoL), work productivity, and indirect and direct costs. Before matching, the BD-I cohort was younger than the non-BD-I cohort and included more female and white respondents and a greater proportion covered by Medicaid or Medicare. After matching, the BD-I and non-BD-I cohorts had similar characteristics. A total of 5418 respondents (BD-I, n = 1806; matched controls, n = 3612) were analyzed. Obese respondents with BD-I reported the highest adjusted prevalences of high blood pressure (50%), high cholesterol (35%), sleep apnea (27%), osteoarthritis (17%), type2 diabetes (12%), and liver disease (4%). Obesity in respondents with BD-I was associated with the lowest HRQoL scores. Measures of work impairment were highest in respondents with BD-I and obesity, as was HCRU. Respondents with BD-I and obesity had the highest associated total indirect and direct medical costs ($25,849 and $44,482, respectively). Obese respondents with BD-I had greater frequencies of obesity-related comorbidities, higher HCRU, lower HRQoL, greater work impairments, and higher indirect and direct medical costs. These findings highlight the real-world burden of obesity in people with BD-I and the importance of considering treatments that may reduce this burden.

Quality and trade with many countries and industries

This paper investigates a trade model with horizontal and vertical product differentations, many goods and many countries. It studies the impact of productivity, population changes and trade costs on the quality composition of exports. The analysis embeds within the same tractable model a series of empirical results, including Linder hypothesis and high-income countries’ specialization in high quality good production. It also shows that high-quality goods exhibiting a high degree of differentiation are traded only by high-income countries.

PRODUKTIVITAS ALAT BERAT PADA PEMBANGUNAN PROYEK IRIGASI RENTANG LSS-07 DI RAMBATAN WETAN KABUPATEN INDRAMAYU

The selection of heavy equipment affects the efficiency and profitability of construction work. The level of effectiveness of heavy equipment is assessed based on the productivity of the equipment. Productivity is the result of dividing output by input. The selection of heavy equipment is something important and must be considered so that its use is efficient and effective because it will affect the productivity of the machine. In the Rentang irrigation network construction project, there are several jobs that use heavy equipment such as piling and excavation work. The heavy equipment chosen must be right so that the project or work runs smoothly. The purpose of this study was to determine the productivity of heavy equipment, volume, number of heavy equipment and the time and cost of implementing heavy equipment. This study is limited to the problem of heavy equipment productivity, volume and time and cost of using heavy equipment. The heavy equipment used in the Rentang irrigation construction in Rambatan Wetan, Indramayu Regency is the PC 200 Excavator, the Sany SY215C Mini Excavator, and the Dump Truck. The productivity of the literature excavation excavator is 344 m3/hour, while the field data excavation is 377.68 m3/hour, the literature excavation dump truck according to the location of the dump truck work in Rambatan Wetan Village, Sindang District is 133.64 m3/hour.

A COMPARATIVE STUDY OF MANUAL TRACTION AND MECHANICAL TRACTION ON ACUTE DISCOGENIC PAIN

Background and purpose: Acute low back pain is defined as Low back pain that has been present for less than three months and it was estimated that 80% of the population suffers from low back pain (LBP) at some point of their lives. Low back pain is the primary factors which limit activity in patients less than 45 years old and it is of significant socio-economic relevance because it may lead to temporary loss of productivity, enormous medical and indirect costs or even leads to permanent disability. The purpose of study was to compare a manual traction versus mechanical traction for reduce acute discogenic pain. Method: The study was conducted at JKK Munirajah Medical Research Foundation college of physiotherapy Out Patient department 30 subjects were selected in random sampling method. They were divided into 2 Group, namely Group A and Group B with 15 subjects in each Group. The enrolled 30 subjects were randomly allotted to two Group A (15) &amp;B (15).After recruitment on eligibility, informed consent is obtained on explaining the treatment to be given. Result: The result showed that there was statistical significant difference between Group A and B. The acute discogenic pain patient who was treated with manual traction had shown good improvement in reduction of acute discogenic pain. Conclusion: The study concluded that there was a statistically significant improvement in reduction of pain improving flexibility and functional ability after the treatment of manual traction for 4 weeks. Thus the study concluded that manual traction (MAT) was the effective treatment than mechanical traction (MET) of acute discogenic low back pain.

Trade‐offs between labour migration and agricultural productivity: Evidence from smallholder wheat systems in Nepal

AbstractRural labour out‐migration has become a major contributor to off‐farm income through remittances and plays a crucial role in supporting the livelihoods of rural households in developing economies. However, research on the simultaneous on‐farm and off‐farm impacts of labour migration is still lacking. This study assesses the impacts of household labour migration on wheat productivity, labour and total costs, profitability and off‐farm income among smallholder wheat growers in Nepal. We use endogenous switching regression and two‐stage least squares regression models to control for potential endogeneity. The findings reveal that labour migration boosts off‐farm income due to remittances but negatively affects wheat productivity and profitability due to labour shortages. In addition, heterogeneous effects are observed, with large farms, cooperative membership, use of farm mechanization and non‐marginalized castes recording positive impacts. The study suggests that social institutions, such as cooperatives, and farm mechanization can create synergies between labour migration and agricultural productivity in Nepal.

Social Costs of Smoking in the Czech Republic.

Smoking is an important risk factor leading to many diseases, which brings substantial healthcare costs as well as indirect costs due to decreased productivity. This article aims to quantify the social costs of smoking in the Czech Republic in 2019. The prevalence-based, cost-of-illness approach is used, which assesses the costs as the sum of direct (healthcare) costs and indirect costs (productivity losses due to mortality and morbidity). The costs of healthcare utilization and pharmacotherapy in direct costs, and the costs of absenteeism, presenteeism, and premature mortality in indirect costs, are included. Total costs of smoking in the Czech Republic in 2019 are estimated as 2110.6 million EUR (0.94% of GDP). Direct costs amounted to 537.0 million EUR (2.9% of health expenditures in 2019) and indirect costs were 1573.6 million EUR, mainly driven by the costs of premature mortality (1062.5 million EUR). Despite the declining trend in the prevalence of smoking in the Czech Republic, the associated costs are considerable. Investments into strategies to reduce smoking continue to be needed.

Industrial IoT-Based Energy Monitoring System: Using Data Processing at Edge

Edge-assisted IoT technologies combined with conventional industrial processes help evolve diverse applications under the Industrial IoT (IIoT) and Industry 4.0 era by bringing cloud computing technologies near the hardware. The resulting innovations offer intelligent management of the industrial ecosystems, focusing on increasing productivity and reducing running costs by processing massive data locally. In this research, we design, develop, and implement an IIoT and edge-based system to monitor the energy consumption of a factory floor’s stationary and mobile assets using wireless and wired energy meters. Once the edge receives the meter’s data, it stores the information in the database server, followed by the data processing method to find nine additional analytical parameters. The edge also provides a master user interface (UI) for comparative analysis and individual UI for in-depth energy usage insights, followed by activity and inactivity alarms and daily reporting features via email. Moreover, the edge uses a data-filtering technique to send a single wireless meter’s data to the cloud for remote energy and alarm monitoring per project scope. Based on the evaluation, the edge server efficiently processes the data with an average CPU utilization of up to 5.58% while avoiding measurement errors due to random power failures throughout the day.

Assessing a decade of leukaemia-related premature mortality costs: impact on productivity loss in Spain.

Cancer mortality is one of the dominant causes of productivity loss; and within all cancer sites, blood cancer is the fourth most common cause of death in Spain. Thus, its impacts in work productivity are a major concern and represent a high social impact. The aim of this study was to evaluate the productivity losses resulting from of premature deaths due to leukaemia in Spain. The productivity costs stemming from premature mortality due to leukaemia were estimated using the human capital method. Information pertaining to mortality rates, typical incomes, and joblessness figures was gathered throughout a decade-long period spanning from 2012 to 2021. Leukaemia caused 40% of haematological malignancies losses. It represented a 3.39% of all cancer-related deaths. In addition, it was responsible for 7,851 years of potential productive life lost (YPLPLL) in 2021, and productivity losses of €4,206.52million over the 10-year period. All these numbers are relevant for Spain as will help on a more efficient distribution of resource. These productivity losses obtained, highlight the burden of leukaemia on the Spanish population, providing novel data on the number of deaths, trends and productivity losses for this type of cancer. This evaluation offers fresh insights that can aid policymakers in efficiently distributing resources, thereby lessening the economic burden it imposes on individuals of working age.

REVENUE FORECASTING SCENARIOS FOR INTERNATIONAL HOTEL CHAINS

The purpose of the study is to develop a system of balanced scorecards for forecasting the income of hotels belonging to international chains. The subject of the study is the system processes of evaluating the effectiveness of the management analysis system, which are determined on the basis of calculating key performance indicators, and as a result of the integral indicator through the analysis and aggregation of individual functional criteria based on comparison with the reference values of the revenue management model for pricing, load planning and its redistribution between revenue centres. Methodology. The study uses the methods of theoretical and logical generalisation. The article describes a set of strategies and tactics used by international hotel chains to manage the demand for hotel services. The results of the article are to form a model for conducting a detailed operational and financial analysis of the hotel enterprise by revenue centres, which contributes to the development of a strategy. The authors have selected a set of indicators that are used to ensure a balanced approach to measuring performance through the indicator method and visual representation in a graphical representation. The paper analyses the performance of international hotel chains over twelve years in order to assess the impact of key factors on their revenues and develop forecasts; the estimated indicators were classified into seven groups: assessment of the average daily revenue per room, room cost, occupancy rate, market share, staff productivity, resource intensity and digitalisation costs. The publication uses the example of international hotel chains to clarify the content and importance of revenue forecasting in the revenue management system.

Beyond Medical Bills: The Indirect Costs of Prostate Cancer.

Both direct and indirect costs contribute to financial toxicity in prostate cancer. Indirect costs are difficult to assess and quantify and therefore remain understudied. We sought to describe the indirect costs of prostate cancer across risk groups as well as identify any associated sociodemographic factors. Patients with localized prostate cancer were surveyed regarding their indirect costs at baseline and 3, 6, 12, and 24-month follow-ups. "Out-of-pocket indirect costs" were defined as costs paid for medication, parking, transportation, meals outside the home, and caregivers. "Imputed indirect costs" were calculated based on hour estimates for traveling time, missed work, additional time spent on work, and additional time dedicated to their care by caregivers. Generalized linear model regressions were performed to evaluate for potential associations between sociodemographic or clinical features with these indirect costs, stratifying by prostate cancer risk group. Four hundred and ninety five localized prostate cancer patients were included in the analysis. Indirect costs ranged from $154.00 to $717.40 for out-of-pocket and $352 to $3389 for imputed per month and did tend to be higher for higher-risk disease. In regression models, sociodemographic factors did not appear to play a strong role in variation in indirect costs. Within a 24-month follow-up period, we observed that indirect costs of localized prostate cancer range from $608 to $4107 per month when including lost productivity costs. Further work must be done to identify what factors contribute to increased indirect costs and financial toxicity.

Is a 1-year course of methotrexate in patients with arthralgia at-risk for rheumatoid arthritis cost-effective? A cost-effectiveness analysis of the randomised, placebo-controlled TREAT EARLIER trial

ObjectivesRheumatoid arthritis (RA) has a considerable disease burden with life-long physical limitations, reduced work productivity and high societal costs. Trials on arthralgia at-risk for RA are therefore conducted, aiming to...

Predicting costs of local public bus transport services through machine learning methods

The present study developed several machine learning-based cost models to predict an efficient total economic cost per vehicle revenue-mile of urban public bus transport. The models were trained on a built-in dataset from 269 transit agencies providing urban services in the United States from 2015 to 2019. A feature selection strategy was implemented, finding that, for each proposed model, a subset of features determined a large impact on unit cost. These “core” features included commercial speed, average salary expenses per employee, vehicle productivity, and fleet ownership cost per vehicle. Machine learning techniques outperformed the linear regression method in terms of predictive power and robustness (understood as the dispersion of predictive power measures over the training sets). Based on SHAP values, the sensitivity analyses showed that the proposed models could be used to predict the impact of changes in some critical features on corresponding unit costs. The results may be useful for: (i) introducing regulatory constraints to the allocation of national public resources to local public bus transport services, aimed at minimizing the resources needed to provide a given level of service; (ii) defining the maximum economic compensation required by firms involved in competitive tendering for the allotment of service concessions, or firms with monopoly rights (by political choice and/or local public ownership); and (iii) improving service contract management and design by identifying key cost drivers of transit services.