Bankroto prognozavimas Lietuvos maitinimo paslaugų sektoriuje: tradicinių, mašininio mokymosi ir hibridinių modelių taikymas bei makroekonominių veiksnių įtaka

Food waste has formidable detrimental impacts on food security, the environment, and the economy, which makes it a global challenge that requires urgent attention. This study investigates the patterns and causes of food waste generation in the hospitality and food service sector, with the aim of identifying the most promising food waste prevention measures. It presents a comparative analysis of five case studies from the hospitality and food service (HaFS) sector in Malaysia and uses a mixed-methods approach. This paper provides new empirical evidence to highlight the significant opportunity and scope for food waste reduction in the HaFS sector. The findings suggest that the scale of the problem is even bigger than previously thought. Nearly a third of all food was wasted in the case studies presented, and almost half of it was avoidable. Preparation waste was the largest fraction, followed by buffet leftover and then customer plate waste. Food waste represented an economic loss equal to 23% of the value of the food purchased. Causes of food waste generation included the restaurants’ operating procedures and policies, and the social practices related to food consumption. Therefore, food waste prevention strategies should be twofold, tackling both the way the hospitality and food service sector outlets operate and organise themselves, and the customers’ social practices related to food consumption.

Machine learning for severe coronary artery disease: classification performance for screening and individualized risk prediction

The restaurant and food service industry sectors are important food system actors who feed millions of customers daily. These sectors offer a variety of inexpensive and convenient meals either consumed by customers on the premises, through takeaway, or delivered at home though new mobile technology. They have the capacity to adopt comprehensive policies and use marketing-mix and choice-architecture strategies to create sustainable food systems that are healthy, humane, fair and socially just, affordable and profitable. These food service sectors can encourage healthy and sustainable food systems that foster the concept of “one health” for people, animals, the environment and planet. This chapter explores current trends, business opportunities and challenges for the transnational restaurant sector to improve the diet quality and health of populations, and to reduce this sector’s adverse impact on the environment. It also discusses emerging technology and restaurant partnerships with delivery service businesses. The opportunities and challenges described are applicable to independent takeaway food establishments and the hospitality and food service sectors to promote healthy and sustainable food systems that align with one health and the UN 2030 Sustainable Development agenda.

Many researchers have focused on developing bankruptcy prediction models using modeling techniques, such as statistical methods including multiple discriminant analysis (MDA) and logit analysis or artificial intelligence techniques containing artificial neural networks (ANN), decision trees, and support vector machines (SVM), to secure enhanced performance. Most of the bankruptcy prediction models in academic studies have used financial ratios as main input variables. The bankruptcy of firms is associated with firm’s financial states and the external economic situation. However, the inclusion of qualitative information, such as the economic atmosphere, has not been actively discussed despite the fact that exploiting only financial ratios has some drawbacks. Accounting information, such as financial ratios, is based on past data, and it is usually determined one year before bankruptcy. Thus, a time lag exists between the point of closing financial statements and the point of credit evaluation. In addition, financial ratios do not contain environmental factors, such as external economic situations. Therefore, using only financial ratios may be insufficient in constructing a bankruptcy prediction model, because they essentially reflect past corporate internal accounting information while neglecting recent information. Thus, qualitative information must be added to the conventional bankruptcy prediction model to supplement accounting information. Due to the lack of an analytic mechanism for obtaining and processing qualitative information from various information sources, previous studies have only used qualitative information. However, recently, big data analytics, such as text mining techniques, have been drawing much attention in academia and industry, with an increasing amount of unstructured text data available on the web. A few previous studies have sought to adopt big data analytics in business prediction modeling. Nevertheless, the use of qualitative information on the web for business prediction modeling is still deemed to be in the primary stage, restricted to limited applications, such as stock prediction and movie revenue prediction applications. Thus, it is necessary to apply big data analytics techniques, such as text mining, to various business prediction problems, including credit risk evaluation. Analytic methods are required for processing qualitative information represented in unstructured text form due to the complexity of managing and processing unstructured text data. This study proposes a bankruptcy prediction model for Korean small- and medium-sized construction firms using both quantitative information, such as financial ratios, and qualitative information acquired from economic news articles. The performance of the proposed method depends on how well information types are transformed from qualitative into quantitative information that is suitable for incorporating into the bankruptcy prediction model. We employ big data analytics techniques, especially text mining, as a mechanism for processing qualitative information. The sentiment index is provided at the industry level by extracting from a large amount of text data to quantify the external economic atmosphere represented in the media. The proposed method involves keyword-based sentiment analysis using a domain-specific sentiment lexicon to extract sentiment from economic news articles. The generated sentiment lexicon is designed to represent sentiment for the construction business by considering the relationship between the occurring term and the actual situation with respect to the economic condition of the industry rather than the inherent semantics of the term. The experimental results proved that incorporating qualitative information based on big data analytics into the traditional bankruptcy prediction model based on accounting information is effective for enhancing the predictive performance. The sentiment variable extracted from economic news articles had an impact on corporate bankruptcy. In particular, a negative sentiment variable improved the accuracy of corporate bankruptcy prediction because the corporate bankruptcy of construction firms is sensitive to poor economic conditions. The bankruptcy prediction model using qualitative information based on big data analytics contributes to the field, in that it reflects not only relatively recent information but also environmental factors, such as external economic conditions.

The COVID-19 pandemic caused a surge in consumption of single-use plastics (SUPs), particularly in the food service sector, due to concerns for public health and safety. To follow public health guidelines, food services have been limited to takeout service and have restricted use of personal reusable items. This study investigated opportunities to reduce increased use of SUPs in Nova Scotia food services sparked by the COVID-19 pandemic using semi-structured interviews and focus groups with stakeholders from the food service sector. Many participants had already implemented SUP reduction strategies prior to COVID-19. However, the COVID-19 pandemic forced businesses to rely on SUPs and to pause SUP reduction strategies. Obstacles to SUP reduction included operational challenges from COVID-19 restrictions, misunderstanding of local waste management systems, costs of transitioning to zero plastic waste, poorly manufactured alternatives, greenwashing, and ingrained societal convenience culture. Whilst not all SUP consumption patterns were attributed to COVID-19, these barriers prevented food retailers, waste managers and consumers from achieving zero-plastic waste goals. Food services should adopt SUP reduction strategies, including re-introducing reusables, implementing exchange programs for bulk items and takeout, providing education and awareness to staff and consumers, and sourcing sustainable SUP alternatives. SUP reduction strategies can be implemented immediately as public health officials and researchers agree reusable items can be used safely when using basic hygiene measures. Food services across Nova Scotia should adapt their operational procedures and create behaviour change to reduce SUPs.

The UK government has been calling for action in tackling food waste (FW) generation, to which the Hospitality and Food Services (HaFS) sector contributes substantially. Decision-making tools that inform the selection of appropriate FW management (FWM) processes in the HaFS sector are lacking. This study fills this gap by offering a conceptual decision-making tool that supports selecting appropriate and commercially available FW processing techniques for the HaFS sector. The study initially conducted an exploratory analysis of on-site and off-site FWM options commercially available in the UK to inform the development of a two-tier decision-making framework. A set of steering criteria was developed and refined via stakeholder consultations to create flowcharts that guide the selection of FWM options, i.e., Tier 1 of the framework. Tier 2 refines the FWM process selection using a comparative sustainability scorecard of FWM options performance developed through a rapid systematic evidence mapping. The main outcome of this study is a flexible decision-making tool that allows stakeholders to participate in the decision-making process and facilitate the selection of tailored-based FWM processes that better suit their circumstances and needs. This approach to decision-making is more likely to enable solutions that facilitate the sustainable management of wasted resources and promote circularity.

The Hospitality and Food Service (HaFS) sectors are notoriously known for their contribution to the food waste problem. Hence, there is an urgent need to devise strategies to reduce food waste in the HaFS sectors and to decarbonise their operation to help fight hunger, achieve food security, improve nutrition and mitigate climate change. This study proposes three streams to decarbonise the staff cafeteria operation in an integrated resort in Macau. These include upstream optimisation to reduce unserved food waste, midstream education to raise awareness amongst staff about the impact of food choices on the climate and health, and finally downstream recognition to reduce edible plate waste using a state-of-the-art computer vision system. Technology can be an effective medium to facilitate desired behavioural change through nudging, much like how speed cameras can cause people to slow down and help save lives. The holistic and data-driven approach taken revealed great potential for organisations or institutions that offer catering services to reduce their food waste and associated carbon footprint whilst educating individuals about the intricate link between food, climate and well-being.

Estimating the risk of bankruptcy of a company has significant economic impact for its owners, investors. In order to determine the risk of bankruptcy or, in other words, success or failure of the company in the future, different models are presented in the literature. The two prominent ones are the Ohlson O-score and the Altman Z-score models. Instead of evaluating all the balance sheets published in the past, these models estimate the bankruptcy risk, taking into account the latest published balance sheet, ie local data rather than historical data. The purpose of this study is to evaluate the risk of bankruptcy risk of the companies, the effect of the performance of the company in the past years, taking into account the effect of more successful estimates can be done. Therefore, the machine learning model has been formed and the predicted success of the model has been investigated on the balance sheet data, which is the label of the company on the risk of bankruptcy in previous periods. In the pre-processing stage of the model, the Information Gain and Principle Component Analysis approaches for the selection of attributes; Logistic Regression, Support Vector Machine and Random Forest are used as machine learning algorithm. The results revealed that a model learning from the previous balance sheet data estimates more successful bankruptcy risk than the financial models that decide on the basis of local data.

Financial distress leading to corporate or institutional failure result in significant losses of economic value, employment, personal income, and tax revenues. For almost a century, researchers have studied the problems and have proposed alternate models for bankruptcy prediction - traditional as well as non￾traditional such as the use of neural networks. The motivation for the utilization of bankruptcy prediction models could be self- improvement, regulatory purposes, investment purposes, and so on. However, smaller business organizations and individual investors are not likely to have the resources and technology to utilize the more complex models. An analysis utilizing the KPP model presented in this study shows that the credit risk profiles generated by this model are excellent predictors of financial distress and bankruptcy risk. The KPP model also acts as an early warning signal since bankruptcy could be predicted as far back as five years before the date of bankruptcy.

The paper is mainly devoted to the bankruptcy prediction models and their ability to assess a bankruptcy probability for Lithuanian companies. The study showed that the most common type of companies in Lithuania is a private limited company, therefore, the main objective was to analyse such companies’ financial information and by using these results, create a new bankruptcy prediction model, which would allow to predict the bankruptcy probability as accurately as possible. 145 companies (73 already bankrupt and 72 still operating) were chosen as a primary sample and by using multivariate discriminant analysis stepwise method a linear function ZGS has been created. To achieve that, 156 different financial ratios were selected as a primary input data by using correlation calculation between bankruptcy and still operating companies and Mann – Whitney U test techniques. The results showed that 89% of companies were classified correctly, which states that the model is strong enough to predict bankruptcy probability for private limited companies operating in Lithuania in a sufficient accuracy.

The European food service market was estimated, in 1999, to be worth US$293 billion with high profit margins and a growth rate of 2.75%. Future demand for value‐added products and high levels of customization will stress the issue of keeping profit margins in the food service industry. Packaging is a critical issue, because it adheres to the product throughout the entire food service supply chain. Package design influences the efficiency of the entire chain in terms of functions, features, information and cost aspects. The purpose of this study was to explore the demands of value‐added packaging in the food service sector and was carried out in the UK. The study shows that there are opportunities to improve packaging solutions to fit better with food service needs. The study also indicates a lack of understanding in the food service sector and that packages can actually add value to the products. Suggested opportunities in package development are presented.

With the prevalence of eating out increasing, the food service sector has an increasing role in accelerating the transition towards more sustainable and healthy food systems. While life cycle-based approaches are recommended to be used as reference methods for assessing the environmental sustainability of food systems and supply chains, their application in the food service sector is still relatively scarce. In this study, a systematic review was conducted to examine the use and effectiveness of life-cycle based interventions in improving the sustainability of food services. This review found that life-cycle based approaches are not only useful for identifying hotspots for impact reduction, but also for comparing the performance of different sustainability interventions. In particular, interventions targeting the production phase, such as promoting dietary change through menu planning in which high-impact ingredients (e.g., animal products) are replaced with low-impact ingredients (e.g., plant foods), had the highest improvement potential. Interventions targeting other phases of the catering supply chain (e.g., food storage, meal preparation, waste management) had considerably lower improvement potentials. This review article provides valuable insights on how the sustainability of the food service sector can be improved without the burden shifting of impacts, which interventions to prioritise, and where knowledge gaps in research exist. A key recommendation for future research is to focus on combined life cycle thinking approaches that are capable of addressing sustainability holistically in the food service sector by integrating and assessing the environmental, social and economic dimensions of interventions.

The Scottish economy, such as the United Kingdom (UK) economy, has been exposed to several adverse shocks over the past 5 years. Examples of these are the effect of the United Kingdom exiting the European Union (Brexit), the effects of the COVID-19 pandemic, and more recently Russia–Ukraine war, which can result in adverse direct and indirect economic losses across various sectors of the economy. These shocks disrupted the food and drink supply chains. The purpose of this article is 3-fold: (1) to explore the degree of resilience of the Scottish food and drink sector, (2) to estimate the effects on interconnected sectors of the economy, and (3) to estimate the economic losses, which is the financial value associated with the reduction in output. This article focuses on the impact that the sudden contraction that the “accommodation and food service activities”, resulting from the pandemic, had on the food and drink sectors. For this analysis, the study relied on the dynamic inoperability input–output model (DIIM), which takes into account the relationships across the different sectors of the Scottish economy over time. The results indicate that the accommodation and food service sector was the most affected by the COVID-19 pandemic lockdown contracting by approximately 60%. The DIIM shows that the disruption to this sector had a cascading effect on the remaining 17 sectors of the economy. The processed and preserved fish, fruits, and vegetable sector is the least resilient, while preserved meat and meat product sector is the most resilient to the final demand disruption in the accommodation and food service sector. The least economically affected sector was the other food product sector, while the other service sector had the highest economic loss. Although the soft drink sector had a slow recovery rate, economic losses were lower compared to the agricultural, fishery, and forestry sectors. From the policy perspective, stakeholders in the accommodation and food service sector should re-examine the sector and develop capacity against future pandemics. In addition, it is important for economic sectors to collaborate either vertically or horizontally by sharing information and risk to reduce the burden of future disruptions. Finally, the most vulnerable sectors of the economy, i.e., other service sectors should form a major part of government policy decision-making when planning against future pandemics.

Developing and validating a machine learning model to predict chronic pain following total knee arthroplasty.

BackgroundBreast cancer-related lymphedema (BCRL) significantly compromises quality of life. Although combined suction-assisted lipectomy (SAL) and lymphovenous anastomosis (LVA) is effective, outcomes vary considerably among patients. Currently, tools for early postoperative risk stratification are lacking.MethodsWe retrospectively reviewed data from BCRL patients who underwent combined SAL and LVA at Beijing Shijitan Hospitalfrom June 2018 to June 2025. Predictive variables were selected using the Least Absolute Shrinkage and Selection Operator (LASSO) regression combined with bootstrap resampling (B = 1,000). Seven algorithms—including logistic regression (LR), decision tree (DT), random forest (RF), eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), support vector machine (SVM), and artificial neural network (ANN) were compared. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), calibration plots, decision curve analysis (DCA), and Brier score. SHapley Additive exPlanations (SHAP) analysis was conducted for model interpretation, and a web-based prediction tool was developed.ResultsA total of 300 patients were enrolled (training set: n=211; validation set: n=89). The rate of satisfactory outcomes at 6 months was 72.3%. LASSO and bootstrap validation identified three stable predictors: postoperative excess limb volume (selection frequency: 100%), disease duration (83.6%), and disease severity grade (83.4%). Among the seven models, SVM exhibited the optimal balance of discrimination and clinical utility in the validation set: AUC 0.891 (95% CI: 0.812–0.970), sensitivity 90.8%, specificity 62.5%, F1-score 0.887, and Brier score 0.119. DCA indicated net clinical benefit within the threshold range of 0.1–0.6. Although ANN achieved a higher AUC than SVM (0.903 vs. 0.891) (DeLong test, P = 0.532), SVM demonstrated superior sensitivity (90.8% vs. 89.2%), F1-score (0.887 vs. 0.879), and Cohen’s kappa (0.555 vs. 0.531).Furthermore, SVM’s structural risk minimization principle conferred superior generalization stability compared with ANN’s empirical risk minimization, making it more suitable for small-sample clinical settings. SHAP analysis revealed that postoperative excess volume was the strongest predictor.ConclusionThe 3-variable SVM model effectively predicts 6-month outcomes following combined surgery for BCRL. Integrated with SHAP analysis and a web-based tool, this model enables early postoperative risk stratification to identify high-risk patients requiring closer monitoring, providing a reference for future standardized rehabilitation protocols.