Search results

The purpose of this paper is to compare nine different models to evaluate consumer credit risk, which are the following: Logistic Regression (LR), Naive Bayes (NB), Linear Discriminant Analysis (LDA), k-Nearest Neighbor (k-NN), Support Vector Machine (SVM), Classification and Regression Tree (CART), Artificial Neural Network (ANN), Random Forest (RF) and Gradient Boosting Decision Tree (GBDT) in Peer-to-Peer (P2P) Lending.

The author uses data from P2P Lending Club (LC) to assess the efficiency of a variety of classification models across different economic scenarios and to compare the ranking results of credit risk models in P2P lending through three families of evaluation metrics.

The results from this research indicate that the risk classification models in the 2013–2019 economic period show greater measurement efficiency than for the difficult 2007–2012 period. Besides, the results of ranking models for predicting default risk show that GBDT is the best model for most of the metrics or metric families included in the study. The findings of this study also support the results of Tsai et al. (2014) and Teplý and Polena (2019) that LR, ANN and LDA models classify loan applications quite stably and accurately, while CART, k-NN and NB show the worst performance when predicting borrower default risk on P2P loan data.

The main contributions of the research to the empirical literature review include: comparing nine prediction models of consumer loan application risk through statistical and machine learning algorithms evaluated by the performance measures according to three separate families of metrics (threshold, ranking and probabilistic metrics) that are consistent with the existing data characteristics of the LC lending platform through two periods of reviewing the current economic situation and platform development.

This study aims to evaluate Artificial Intelligence (AI) research in the hospitality industry based on the service AI framework (mechanical-thinking-feeling) and highlight prospective avenues for future inquiry in this growing domain.

This paper conceptualizes timely concepts supported by research spanning multiple domains.

This research introduces a novel classification for the domain of AI hospitality research. This classification encompasses prediction and pattern recognition, computer vision, NLP, behavioral research, and synthetic data generation. Based on this classification, this study identifies and elaborates upon five emerging research topics, each linked to a corresponding set of research questions. These focal points encompass the realms of interpretable AI, controllable AI, AI ethics, collaborative AI, and synthetic data generation.

This viewpoint provides a foundational framework and a directional compass for future research in AI within the hospitality industry. It pushes the industry forward with a balanced approach to leveraging AI to augment human potential and enrich customer experiences. Both the classification and the research agenda would contribute to the body of knowledge that will guide the industry toward a future where technology and human service coalesce to create unparalleled value for all stakeholders.

The objective of this study is to investigate the impact of longitudinal forces on extreme-long heavy-haul trains, providing new insights and methods for their design and operation, thereby enhancing safety, operational efficiency and track system design.

A longitudinal dynamics simulation model of the super long heavy haul train was established and verified by the braking test data of 30,000 t heavy-haul combination train on the long and steep down grade of Daqing Line. The simulation model was used to analyze the influence of factors on the longitudinal force of super long heavy haul train.

Under normal conditions, the formation length of extreme-long heavy-haul combined train has a small effect on the maximum longitudinal coupler force under full service braking and emergency braking on the straight line. The slope difference of the long and steep down grade has a great impact on the maximum longitudinal coupler force of the extreme-long heavy-haul trains. Under the condition that the longitudinal force does not exceed the safety limit of 2,250 kN under full service braking at the speed of 60 km/h the maximum allowable slope difference of long and steep down grade for 40,000 t super long heavy-haul combined trains is 13‰, and that of 100,000 t is only 5‰.

The results will provide important theoretical basis and practical guidance for further improving the transportation efficiency and safety of extreme-long heavy-haul trains.

This paper aims to improve the delimitation of plant growth stages in the context of weather index insurance design. We propose a data-driven phase division that minimizes estimation errors in the weather-yield relationship and investigate whether it can substitute an expert-based determination of plant growth phases. We combine this procedure with various statistical and machine learning estimation methods and compare their performance.

Using the example of winter barley, we divide the complete growth cycle into four sub-phases based on phenology reports and expert instructions and evaluate all combinations of start and end points of the various growth stages by their estimation errors of the respective yield models. Some of the most commonly used statistical and machine learning methods are employed to model the weather-yield relationship with each selected method we applied.

Our results confirm that the fit of crop-yield models can be improved by disaggregation of the vegetation period. Moreover, we find that the data-driven approach leads to similar division points as the expert-based approach. Regarding the statistical model, in terms of yield model prediction accuracy, Support Vector Machine ranks first and Polynomial Regression last; however, the performance across different methods exhibits only minor differences.

This research addresses the challenge of separating plant growth stages when phenology information is unavailable. Moreover, it evaluates the performance of statistical and machine learning methods in the context of crop yield prediction. The suggested phase-division in conjunction with advanced statistical methods offers promising avenues for improving weather index insurance design.

Parental leave in Sweden can be taken both as paid and unpaid leave and often parents mix these forms in a very flexible way. Therefore, multiple methodological issues arise regarding how to most accurately measure leave length. The purpose of this paper is to review the somewhat complex legislation and the possible ways of using parental leave before presenting a successful attempt of a more precise way of measuring leave lengths, including paid and unpaid days, for mothers and fathers.

The study makes use of administrative data for a complete cohort of parents of first born children in 2009 in Sweden. The authors examine what characteristics are associated with the use of paid and unpaid leave for mothers and fathers during the first two years of the child’s life, focusing particularly on how individual and household income is associated with leave patterns.

Among mothers, low income is associated with many paid leave days whereas middle income is associated with most unpaid days. High income mothers use a shorter leave. Among fathers it is the both ends with high and low household income that uses most paid and unpaid leave.

A measure that includes unpaid parental leave will be important to not underestimate the parental leave and to prevent faulty comparisons between groups by gender and by socioeconomic status.

A measure of parental leave including both paid and unpaid leave will also facilitate international comparisons of leave length.

Metropolitan areas suffer from frequent road traffic congestion not only during peak hours but also during off-peak periods. Different machine learning methods have been used in travel time prediction, however, such machine learning methods practically face the problem of overfitting. Tree-based ensembles have been applied in various prediction fields, and such approaches usually produce high prediction accuracy by aggregating and averaging individual decision trees. The inherent advantages of these approaches not only get better prediction results but also have a good bias-variance trade-off which can help to avoid overfitting. However, the reality is that the application of tree-based integration algorithms in traffic prediction is still limited. This study aims to improve the accuracy and interpretability of the models by using random forest (RF) to analyze and model the travel time on freeways.

As the traffic conditions often greatly change, the prediction results are often unsatisfactory. To improve the accuracy of short-term travel time prediction in the freeway network, a practically feasible and computationally efficient RF prediction method for real-world freeways by using probe traffic data was generated. In addition, the variables’ relative importance was ranked, which provides an investigation platform to gain a better understanding of how different contributing factors might affect travel time on freeways.

The parameters of the RF model were estimated by using the training sample set. After the parameter tuning process was completed, the proposed RF model was developed. The features’ relative importance showed that the variables (travel time 15 min before) and time of day (TOD) contribute the most to the predicted travel time result. The model performance was also evaluated and compared against the extreme gradient boosting method and the results indicated that the RF always produces more accurate travel time predictions.

This research developed an RF method to predict the freeway travel time by using the probe vehicle-based traffic data and weather data. Detailed information about the input variables and data pre-processing were presented. To measure the effectiveness of proposed travel time prediction algorithms, the mean absolute percentage errors were computed for different observation segments combined with different prediction horizons ranging from 15 to 60 min.

In this digital era, email is the most pervasive form of communication between people. Many users become a victim of spam emails and their data have been exposed.

Researchers contribute to solving this problem by a focus on advanced machine learning algorithms and improved models for detecting spam emails but there is still a gap in features. To achieve good results, features also play an important role. To evaluate the performance of applied classifiers, 10-fold cross-validation is used.

The results approve that the spam emails are correctly classified with the accuracy of 98.00% for the Support Vector Machine and 98.06% for the Artificial Neural Network as compared to other applied machine learning classifiers.

In this paper, Point-Biserial correlation is applied to each feature concerning the class label of the University of California Irvine (UCI) spambase email dataset to select the best features. Extensive experiments are conducted on selected features by training the different classifiers.

This chapter demonstrates that social business models do not meaningfully prioritize or impose accountability to “social good” over other purposes in ways that (a) best protect against owners changing their minds or entry of new owners with different priorities and (b) enable reliable accountability over time and across circumstances. This chapter further suggests a model – a “social primacy company” – that actually prioritizes “social good” and meaningful accountability to it. This chapter thus clarifies circumstances under which existing models might be most useful and are not particularly useful, especially as investors, entrepreneurs, employees, regulators, and others pursue shared, common understandings about purposes, priorities, and accountability.

This research explores how contextual elements and significant events influence the changing storylines within a company's directors' reports spanning a period of six decades. These elements and events encompass the internal dynamics of the family that owns the company, industry-specific advancements, political and socioeconomic climates, and explicit guidelines related to corporate reporting.

This research employs a case study methodology to analyse the directors' reports of Barilla, a prominent Italian food manufacturer, within the theoretical framework of historical institutionalism. A systematic content analysis is conducted on sixty directors' reports published between 1961 and 2021. The study also identifies and examines significant contextual events within this six-decade period, which are linked to four key institutional factors.

Based on the research findings, the directors' reports exhibited notable fluctuations throughout the studied timeframe in reaction to shifts in the institutional setting. Our investigation highlights that each institutional element experienced crucial pivotal moments, and given their interconnected nature, modifications in one factor impacted the others. It was noted that these pivotal moments resulted in alterations in the directors' reports' content across various thematic areas. Additionally, despite Barilla being a multinational company, it was found that national events within Italy had a more pronounced influence on the evolving narratives than global events.

Previous research on directors' reports or chairman's statements has primarily focused on the influence of macro-level institutional factors on the narratives. In contrast, our study considers both macro-level and micro-level institutions, specifically examining the internal events within a family business and how they shape the content of directors' reports. Our study is also distinctive in its analysis of specific critical junctures and their interactions with the investigated institutional factors. Additionally, to the best of our knowledge, few existing studies span a timeframe of sixty years, particularly concerning an Italian company.