Explore the vast range of titles available.

Purpose The purpose of this paper is to elucidate the emerging landscape of procurement analytics. This paper focuses on the following questions: what are the current and future state of procurement analytics?; what changes in the procurement process will be required to enable integration of analytical solutions?; and what future areas of research arise when considering the future state of procurement analytics? Design/methodology/approach This paper employs a qualitative approach that relies on three sources of information: executive interviews, a review of current and emerging technology platforms and a small survey of subject matter experts in the field. Findings The procurement analytics landscape developed in this research suggests that the authors will continue to see major shifts in the sourcing and supply chain technology environment in the next five years. However, there currently exists a low usage of advanced procurement analytics, and data integrity and quality issues are preventing significant advances in analytics. This study identifies the need for organizations to establish a coherent approach to collection and storage of trusted organizational data that build on internal sources of spend analysis and contract databases. In addition, current ad hoc approaches to capturing unstructured data must be replaced by a systematic data governance strategy. An important element for organizations in this evolution is managing change and the need to nourish an analytic culture. Originality/value While the majority of forward-looking research and reports merely project broad technological impact of cognitive analytics and big data, much of it does not provide specific insights into functional impacts such as the impact on procurement. The analysis of this study provides us with a clear view of the potential for business analytics and cognitive analytics to be employed in procurement processes, and contributes to development of related research topics for future study. In addition, this study suggests detailed implementation strategies of emerging procurement technologies, contributing to the existing body of the literature and industry reports.

PurposeThe objective of this paper is to study the role of artificial intelligence (AI) in supporting the supplier scouting process, considering the information and the capabilities required to do so.Design/methodology/approachTwelve cases of IT and information providers offering AI-based scouting solutions were studied. The unit of analysis was the AI-based scouting solution, specifically the relationship between the provider and the buyer. Information processing theory (IPT) was adopted to address information processing needs (IPNs) and capabilities (IPCs).FindingsAmong buyers, IPNs in supplier scouting are high. IT and information providers can meet the needs of buyers through IPCs enabled by AI-based solutions. In this way, the fit between needs and capabilities can be reached.Originality/valueThe investigation of the role of AI in supplier scouting is original. The application of IPT to study the impact of AI in business processes is also novel. This paper contributes by investigating a phenomenon that is still unexplored and unconsolidated in a business context.

PurposeThis study examines green absorptive capacity as an important intervening variable that elucidates the relationship between green supply chain management (GSCM) practices (specifically, green purchasing, customer cooperation and investment recovery) and firm performance.Design/methodology/approachDrawing from the theoretical underpinnings of the natural-resource-based view theory and information processing theory, a research model is developed and tested using data obtained from 368 manufacturing firms in Ghana. Data analysis was conducted using structural equation modeling.FindingsThe results indicate that green purchasing, customer cooperation and investment recovery have a direct positive and significant effect on firm performance. Additionally, green purchasing and customer cooperation have a positive and significant effect on green absorptive capacity but investment recovery does not. Further, the results show that the paths from green purchasing and customer cooperation to firm performance are positively mediated by green absorptive capacity.Practical implicationsThe study reveals to supply chain managers that green absorptive capacity is an important conduit through which firms can achieve enhanced firm performance from GSCM initiatives.Originality/valueThis study makes a contribution by integrating the absorptive capacity literature and green management literature and establishes green absorptive capacity as a mechanism through which GSCM practices enhance firm performance.

BackgroundDespite demonstrated influence of country of residence on labour force participation among patients with RA, little attempt has been made to understand the users' perceptions of support and social security (SS) systems.ObjectivesTo explore the patterns in perceptions among patients with RA and rheumatologists from different European countries across five domains (1) importance and support to remain employed, (2) process of applying for WD, (3) obtaining and living with WD pension, (4) role of the rheumatologists in support to remain employed or apply for WD pension and (5) performance of the system.MethodsA survey among RA patients and rheumatologists was conducted in 44 countries of European WHO Region. For each domain, several questions (4 to 6 questions per domain, each on a 1–5 Likert answer scale, dichotomized as 1 (“totally (agree)”) and 0 (“not agree, not disagree”, “totally (disagree)”) were asked (Table). Next, sum scores were calculated for each domain and averaged per country. The domain “remaining employed” was assessed in patients who currently have or ever had work. Analyses in domains “process of applying for WD” and “obtaining and living with WD” were limited to patients who currently have or ever considered applying for WD. Comparisons of scores in all domains were explored by: EU-15, new EU member states and non-EU countries, the five types of social welfare system (Anglo-Saxon, Bismarckian, Mediterranean, Post-Communist, and Scandinavian) and by countries' wealth (GDP per capita adjusted for purchasing power parity [PPP]) using ANOVA or Pearson correlation, as appropriate.ResultsOf 44 countries, 31 (70%) and 30 (68%) have provided data for patients and rheumatologists, respectively. In total, 646 patients (mean age (SD) 53 (12), 76% female, 519 (78%) ever worked) and 500 rheumatologists filled in the questionnaires. Overall, positive weak to no relationships were present between the GDP per capita and perceptions from rheumatologists or patients about SS arrangements. However, significant differences were observed across the systems type with the Scandinavian type (Finland, Norway, Sweden) consistently scoring higher than the others on most domains (table). Remarkably, rheumatologists in less wealthy and non-EU countries felt more confident in their role related to WD pension.ConclusionsPatients'a nd rheumatologists' perceptions of systems to support persons with RA encountering work restrictions varied mostly according to the type of the social welfare system, while remarkably little differences were related to country's wealth and membership in EU. Scandinavian employment support and social security system appeared to most adequately meet the expectations of patients and rheumatologists in questions of remaining at work and application to WD pension.Disclosure of InterestNone declared

The coronavirus disease 2019 pandemic has impacted and changed consumer behavior because of a prolonged quarantine and lockdown. This study proposed a theoretical framework to explore and define the influencing factors of online consumer purchasing behavior (OCPB) based on electronic word-of-mouth (e-WOM) data mining and analysis. Data pertaining to e-WOM were crawled from smartphone product reviews from the two most popular online shopping platforms in China, Jingdong.com and Taobao.com . Data processing aimed to filter noise and translate unstructured data from complex text reviews into structured data. The machine learning based K-means clustering method was utilized to cluster the influencing factors of OCPB. Comparing the clustering results and Kotler’s five products level, the influencing factors of OCPB were clustered around four categories: perceived emergency context, product, innovation, and function attributes. This study contributes to OCPB research by data mining and analysis that can adequately identify the influencing factors based on e-WOM. The definition and explanation of these categories may have important implications for both OCPB and e-commerce.

In this paper, we propose a real-time online shopper behavior analysis system consisting of two modules which simultaneously predicts the visitor’s shopping intent and Web site abandonment likelihood. In the first module, we predict the purchasing intention of the visitor using aggregated pageview data kept track during the visit along with some session and user information. The extracted features are fed to random forest (RF), support vector machines (SVMs), and multilayer perceptron (MLP) classifiers as input. We use oversampling and feature selection preprocessing steps to improve the performance and scalability of the classifiers. The results show that MLP that is calculated using resilient backpropagation algorithm with weight backtracking produces significantly higher accuracy and F1 Score than RF and SVM. Another finding is that although clickstream data obtained from the navigation path followed during the online visit convey important information about the purchasing intention of the visitor, combining them with session information-based features that possess unique information about the purchasing interest improves the success rate of the system. In the second module, using only sequential clickstream data, we train a long short-term memory-based recurrent neural network that generates a sigmoid output showing the probability estimate of visitor’s intention to leave the site without finalizing the transaction in a prediction horizon. The modules are used together to determine the visitors which have purchasing intention but are likely to leave the site in the prediction horizon and take actions accordingly to improve the Web site abandonment and purchase conversion rates. Our findings support the feasibility of accurate and scalable purchasing intention prediction for virtual shopping environment using clickstream and session information data.

This study establishes a deep learning model for personalized travel recommendations based on factors that affect tourists’ purchases to provide users with more accurate and personalized travel recommendations. Firstly, Natural Language Processing (NLP) technology is used to process and emotionally analyze tourism review information, dividing it into positive, negative, or neutral to understand tourists’ attitudes towards purchasing products and services. Secondly, a High-Performance Network (HPN) model is constructed based on factors that affect tourists’ purchases. The relationship among tourists, products, and word of mouth (WOM) is represented as a complex network to analyze and predict event occurrence patterns and influencing factors in tourism electronic word-of-mouth (EWOM) data. The construction of the model considers various factors, such as the spread of WOM, the impact of price, etc., to reveal the complex relationships among tourists, WOM, products, etc. Finally, the Recurrent Neural Network (RNN) model is combined with the Backpropagation (BP) model, the time series data is processed with the help of the gated recurrent unit, and the HPN model is trained and evaluated. The Yelp dataset is employed to verify the accuracy and feasibility of the model, which contains the score and review data of many tourist destinations. The results reveal that price, WOM, and destination are one of the main factors influencing tourists’ purchasing behavior, with WOM being the most significant. Positive WOM reviews remarkably increase product sales, while negative WOM has the opposite effect. The minimum expectation for age, occupation, education, personal monthly income, and tourists’ willingness to purchase is 0.00, and the minimum expectation for gender factors is 0.31. The RNN-BP hybrid model has higher accuracy and predictive ability, which is 1.73% and 2.30% more accurate than single models and traditional machine learning predictive models. In short, this study contributes to a better understanding travelers’ needs and preferences to optimize products and services and improve market competitiveness. In addition, the methods and models of this study can also be applied in EWOM data mining in other fields.

American diets are increasingly based on ultra-processed foods (UPF). Current research, particularly on socio-economic differentials, is lacking. This study aimed to provide an updated examination of US household purchases of UPF and how this differs by race-ethnicity, household income and household education. The NielsenIQ Consumer Panel 2020 was utilised for analysis. Each food and beverage product purchased by US households was assigned a level of processing under the Nova level of processing classification system. The volume of UPF purchased overall and by food group was determined for each Nova processing group and examined by race-ethnicity, education and income. Results were stratified by race-ethnicity within each income group. A value < 0·0001 was considered significant. This study analysed data from the Nielsen IQ Consumer Panel 2020 which recorded household food purchases in the USA. The Nielsen IQ Homescan Consumer Panel is a nationally representative longitudinal survey of around 35 000 and 60 000 US households. Of 33 054 687 products purchased by 59 939 US households in 2020, 48 % of foods and 38 % of beverages were considered UPF. Categories with the highest proportion of purchases deriving from UPF included carbonated soft drinks (90 %), mixed dishes and soups (81 %) and sweets and snacks (71 %). Slightly higher but statistically significant proportions of UPF purchases occurred in the lowest income and education groups and among non-Hispanic whites. It is concerning that household purchases of UPF in the USA are high. Policies that reduce consumption of UPF may help reduce diet-related health inequalities.

The detection of corruption-related indicators within unstructured, textual procurement data remains a complex task due to linguistic ambiguity, contextual variation and domain-specific terminology. This study presents a comparative evaluation of three transformer-based Natural Language Processing (NLP) architectures (BERT-base-uncased, RoBERTa-base and DeBERTa-v3-base) for automated corruption risk indicator detection in procurement texts coming from heterogeneous sources. A unified dataset is constructed by linking unstructured technical documentation with structured procurement outcomes, enabling an outcome-driven risk labeling strategy. Performance evaluation is conducted through different metrics, including precision, recall, F1-score and ROC-AUC, complemented by explainability analysis using Integrated Gradients. The results demonstrate a clear performance progression and highlight the comparative strengths of the evaluated architectures. Overall, this study highlights the potential of contextual transformer models to support scalable, transparent and operational anti-corruption monitoring systems.