Search results

Objectively evaluating the fairness of the algorithm, exploring in specific scenarios combined with scenario characteristics and constructing the algorithm fairness evaluation index system in specific scenarios.

This paper selects marketing scenarios, and in accordance with the idea of “theory construction-scene feature extraction-enterprise practice,” summarizes the definition and standard of fairness, combs the application link process of marketing algorithms and establishes the fairness evaluation index system of marketing equity allocation algorithms. Taking simulated marketing data as an example, the fairness performance of marketing algorithms in some feature areas is measured, and the effectiveness of the evaluation system proposed in this paper is verified.

The study reached the following conclusions: (1) Different fairness evaluation criteria have different emphases, and may produce different results. Therefore, different fairness definitions and standards should be selected in different fields according to the characteristics of the scene. (2) The fairness of the marketing equity distribution algorithm can be measured from three aspects: marketing coverage, marketing intensity and marketing frequency. Specifically, for the fairness of coverage, two standards of equal opportunity and different misjudgment rates are selected, and the standard of group fairness is selected for intensity and frequency. (3) For different characteristic fields, different degrees of fairness restrictions should be imposed, and the interpretation of their calculation results and the means of subsequent intervention should also be different according to the marketing objectives and industry characteristics.

First of all, the fairness sensitivity of different feature fields is different, but this paper does not classify the importance of feature fields. In the future, we can build a classification table of sensitive attributes according to the importance of sensitive attributes to give different evaluation and protection priorities. Second, in this paper, only one set of marketing data simulation data is selected to measure the overall algorithm fairness, after which multiple sets of marketing campaigns can be measured and compared to reflect the long-term performance of marketing algorithm fairness. Third, this paper does not continue to explore interventions and measures to improve algorithmic fairness. Different feature fields should be subject to different degrees of fairness constraints, and therefore their subsequent interventions should be different, which needs to be continued to be explored in future research.

This paper combines the specific features of marketing scenarios and selects appropriate fairness evaluation criteria to build an index system for fairness evaluation of marketing algorithms, which provides a reference for assessing and managing the fairness of marketing algorithms.

Algorithm governance and algorithmic fairness are very important issues in the era of artificial intelligence, and the construction of the algorithmic fairness evaluation index system in marketing scenarios in this paper lays a safe foundation for the application of AI algorithms and technologies in marketing scenarios, provides tools and means of algorithm governance and empowers the promotion of safe, efficient and orderly development of algorithms.

In this paper, firstly, the standards of fairness are comprehensively sorted out, and the difference between different standards and evaluation focuses is clarified, and secondly, focusing on the marketing scenario, combined with its characteristics, key fairness evaluation links are put forward, and different standards are innovatively selected to evaluate the fairness in the process of applying marketing algorithms and to build the corresponding index system, which forms the systematic fairness evaluation tool of marketing algorithms.

From the buying club’s perspective, the transfer of a player can be interpreted as an investment from which the club expects uncertain future benefits. This paper aims to develop a decision-oriented approach for the valuation of football players that could theoretically help clubs determine the subjective value of investing in a player to assess its potential economic advantage.

We build on a semi-investment-theoretical risk-value model and elaborate an approach that can be applied in imperfect markets under uncertainty. Furthermore, we illustrate the valuation process with a numerical example based on fictitious data. Due to this explicitly intended decision support, our approach differs fundamentally from a large part of the literature, which is empirically based and attempts to explain observable figures through various influencing factors.

We propose a semi-investment-theoretical valuation approach that is based on a two-step model, namely, a first valuation at the club level and a final calculation to determine the decision value for an individual player. In contrast to the previous literature, we do not rely on an econometric framework that attempts to explain observable past variables but rather present a general, forward-looking decision model that can support managers in their investment decisions.

This approach is the first to show managers how to make an economically rational investment decision by determining the maximum payable price. Nevertheless, there is no normative requirement for the decision-maker. The club will obviously have to supplement the calculus with nonfinancial objectives. Overall, our paper can constitute a first step toward decision-oriented player valuation and for theoretical comparison with practical investment decisions in football clubs, which obviously take into account other specific sports team decisions.

The purpose of this study is to determine propeller damage based on acoustic recordings taken from unmanned aerial vehicle (UAV) propellers operated at different thrust conditions on a test bench. Propeller damage is especially critical for fixed-wing UAVs to sustain a safe flight. The acoustic characteristics of the propeller vary with different propeller damages.

For the research, feature extraction methods and machine learning techniques were used during damage detection from propeller acoustic data. First of all, sound recordings were obtained by operating five different damaged propellers and undamaged propellers under three different thrusts. Afterwards, the harmonic-to-noise ratio (HNR) feature extraction technique was applied to these audio recordings. Finally, model training and validation were performed by applying the Gaussian Naive Bayes machine learning technique to create a diagnostic approach.

A high recall value of 96.19% was obtained in the performance results of the model trained according to damaged and undamaged propeller acoustic data. The precision value was 73.92% as moderate. The overall accuracy value of the model, which can be considered as general performance, was obtained as 81.24%. The F1 score has been found as 83.76% which provides a balanced measure of the model’s precision and recall values.

This study include provides solid method to diagnose UAV propeller damage using acoustic data obtain from the microphone and allows identification of differently damaged propellers. Using that, the risk of in-flight failures can be reduced and maintenance costs can be lowered with addressing the occurred problems with UAV propeller before they worsen.

This study introduces a novel method to diagnose damaged UAV propellers using the HNR feature extraction technique and Gaussian Naive Bayes classification method. The study is a pioneer in the use of HNR and the Gaussian Naive Bayes and demonstrates its effectiveness in augmenting UAV safety by means of propeller damages. Furthermore, this approach contributes to UAV operational reliability by bridging the acoustic signal processing and machine learning.

This study aims to construct a sentiment series generation method for danmu comments based on deep learning, and explore the features of sentiment series after clustering.

This study consisted of two main parts: danmu comment sentiment series generation and clustering. In the first part, the authors proposed a sentiment classification model based on BERT fine-tuning to quantify danmu comment sentiment polarity. To smooth the sentiment series, they used methods, such as comprehensive weights. In the second part, the shaped-based distance (SBD)-K-shape method was used to cluster the actual collected data.

The filtered sentiment series or curves of the microfilms on the Bilibili website could be divided into four major categories. There is an apparently stable time interval for the first three types of sentiment curves, while the fourth type of sentiment curve shows a clear trend of fluctuation in general. In addition, it was found that “disputed points” or “highlights” are likely to appear at the beginning and the climax of films, resulting in significant changes in the sentiment curves. The clustering results show a significant difference in user participation, with the second type prevailing over others.

Their sentiment classification model based on BERT fine-tuning outperformed the traditional sentiment lexicon method, which provides a reference for using deep learning as well as transfer learning for danmu comment sentiment analysis. The BERT fine-tuning–SBD-K-shape algorithm can weaken the effect of non-regular noise and temporal phase shift of danmu text.

This chapter discusses how the real options theory can be useful for understanding the adoption of human resources management (HRM) practices. The authors review how the real options theory has provided insights into the processes through which firms manage uncertainties involved in the adoption of HRM practices. The authors offer propositions for future HRM research from the real options perspective. The authors contend that analyzing HRM practice adoptions through the lens of real options theory can enhance our understanding of the mechanisms through which firms choose which HRM practices to adopt and how they adjust the timing, scale, and methods of investment in these practices. Specifically, the authors suggest that differences in information relevant to valuation of HRM options are the source of distinct choices of HRM options across firms. Finally, the authors propose advancing knowledge on HRM practice adoptions by using a portfolio of options approach, as well as considering factors like competitors, path dependence, and switching options.

This paper aims to examine the impact of corporate environmental transparency (CET) on corporate financial performance under a mandatory environmental disclosure policy in China, the largest carbon-emitting country. It aims to clarify the concept of CET and investigate its short-term financial implications for key pollutant-discharging entities (KPEs).

A multidimensional model is used to construct a comprehensive CET index for KPEs in China. Empirical tests are conducted to assess the relationship between CET and corporate financial performance.

The study finds a negative relationship between CET and corporate financial performance in the short term. Increased environmental transparency necessitates higher environmental resource allocation, adversely affecting profits. The results remain unchanged from a battery of robustness tests. Despite mandatory disclosure, companies tend to provide general and vague information rather than specific and meaningful environmental data.

The findings provide rich practical implications for policymakers to improve a mandatory environmental disclosure policy. The paper also contributes to the existing knowledge by developing a measure of CET and presenting new evidence to the debate on whether corporate environmental disclosure can be regarded as transparency.

Policymakers are advised to refine mandatory environmental disclosure regulations to ensure genuine transparency and to implement policy measures that alleviate the financial burdens of companies with high CET levels, thereby encouraging sustainable practices.

This paper contributes to the existing knowledge by developing a measure of CET and providing new evidence on the debate over whether environmental, social and governance (ESG) disclosure equates to transparency. It emphasizes the complexity of transparency and the inadequacy of current environmental disclosure practices among KPEs. The study underscores the need for financial support for companies with high CET levels to alleviate short-term financial strains and promote long-term sustainability.

This paper aims to overcome the inability of both comparing loss costs and accounting for production resource losses of Overall Equipment Effectiveness (OEE)-related approaches.

The authors conducted a literature review about the studies focusing on approaches combining OEE with monetary units and/or resource issues. The authors developed an approach based on Overall Equipment Cost Loss (OECL), introducing a component for the production resource consumption of a machine. A real case study about a smart multicenter three-spindle machine is used to test the applicability of the approach.

The paper proposes Resource Overall Equipment Cost Loss (ROECL), i.e. a new KPI expressed in monetary units that represents the total cost of losses (including production resource ones) caused by inefficiencies and deviations of the machine or equipment from its optimal operating status occurring over a specific time period. ROECL enables to quantify the variation of the product cost occurring when a machine or equipment changes its health status and to determine the actual product cost for a given production order. In the analysed case study, the most critical production orders showed an actual production cost about 60% higher than the minimal cost possible under the most efficient operating conditions.

The proposed approach may support both production and cost accounting managers during the identification of areas requiring attention and representing opportunities for improvement in terms of availability, performance, quality, and resource losses.

Art return indices are usually estimated based only on a few means of artistic expression (mainly paintings and drawings). Other forms of expression (e.g. sculptures and installations) are generally ignored, in part because they are three-dimensional and, hence, more difficult to measure. We analyze the price determinants as well as the return and risk of three artistic expressions (paintings, drawings and sculptures) executed by Fernando Botero, the most expensive living Latin American artist, to analyze the degree to which their risk and return attributes differ throughout a 20-year period.

We analyzed all paintings, drawings and sculptures executed by Botero and sold at Sotheby’s and Christie’s between 2000 and 2020 (a total of 707 artworks). The data and the images of each artwork were obtained from the web pages of these two auction houses. A hedonic regression was run to explain the price of each artwork and use explanatory variables that are standard in the literature. Art price indices for paintings, drawings and sculptures were constructed using the year-dummy variables estimated in the regressions. We performed a similar analysis for another artist, Carlos Cruz-Diez, as a robustness to our results.

The performance of Botero’s sculptures through time differs markedly from that of his paintings and drawings. Our results suggest that it is possible that returns estimated in the literature could suffer from a bias, as they have usually ignored the performance of sculptures and other artistic expressions. Botero’s paintings provided a return that was comparable to those of his sculptures (3.36% and 3.20%, respectively), they were two times as high as those of his drawings (1.68%). On the other hand, whereas paintings and drawings had similar annual standard deviations (26% and 25.22%, respectively), sculptures had a much smaller standard deviation (16.96%).

A limitation of the hedonic regression method lies in the need to have a significant and diverse sample to identify the true effect of each variable on the price of a good. Another limitation is that we were only able to use art prices from auctions, as this is the only comprehensive source of art price data that is publicly available. These two limitations are shared by all the studies that use the hedonic pricing model.

Our results have practical applications for art collectors and investors, as well as for artists, galleries and, in general, for the whole art market ecosystem. The risk and return attributes of the various artistic expressions of an artist can be different, and thus it makes sense to analyze each one of them individually, as well as their correlations with the other artistic expressions and with traditional and other alternative investments.

The art market is part of what is known as the “orange economy” (also known as the Creative Economy). According to the World Bank, the economic value of the creative sector is not well known or appreciated, even though cultural, creative and artistic activities are vital for our sense of well-being.

To the best of our knowledge, this is the first paper that compares the financial performance of paintings, drawings and sculptures for the case of a specific artist. We chose Botero for three reasons. First, he is a Latin American living artist who has achieved the highest levels of international sales. Second, Botero has worked extensively on various artistic expressions (oil paintings, drawings on different materials and sculptures) throughout his life, a characteristic that is essential to be able to carry out our study. Third, there is a long record of auction sales for each of Botero’s artistic expressions.

Los índices de rentabilidad del arte generalmente se estiman basándose únicamente en unos pocos medios de expresión artística (principalmente pinturas y dibujos). Otras formas de expresión artística (por ejemplo, esculturas e instalaciones) generalmente se ignoran, en parte porque son tridimensionales y, por tanto, más difíciles de medir. Analizamos los determinantes del precio, así como el retorno y el riesgo de tres expresiones artísticas (pinturas, dibujos y esculturas) ejecutadas por Fernando Botero, el artista latinoamericano vivo más caro, para analizar en qué medida sus atributos de riesgo y retorno difieren a lo largo del tiempo, en un período de 20 años.

Analizamos todas las pinturas, dibujos y esculturas ejecutadas por Botero y vendidas en Sotheby’s y Christie’s entre 2000 y 2020 (un total de 707 obras de arte). Los datos y las imágenes de cada obra se obtuvieron de las páginas web de estas dos casas de subastas. Se realizó una regresión hedonante para explicar el precio de cada obra de arte y se utilizaron variables explicativas estándar en la literatura. Los índices de precios de arte para pinturas, dibujos y esculturas se construyeron utilizando variables ficticias anuales estimadas en las regresiones. Realizamos un análisis similar para otro artista, Carlos Cruz-Diez, como análisis de robustez de nuestros resultados.

El desempeño de las esculturas de Botero a través del tiempo difiere marcadamente del de sus pinturas y dibujos. Nuestros resultados sugieren que es posible que los retornos estimados en la literatura sufran un sesgo, ya que generalmente han ignorado el desempeño de esculturas y otras expresiones artísticas. Las pinturas de Botero proporcionaron un retorno comparable al de sus esculturas (3.36% y 3.20%, respectivamente), pero fueron dos veces superiores a los de sus dibujos (1.68%). Por otro lado, mientras que las pinturas y los dibujos tuvieron desviaciones estándar anuales similares (26% y 25.22%, respectivamente), las esculturas tuvieron una desviación estándar mucho menor (16.96%).

Una limitación del método de regresión hedónica radica en la necesidad de contar con una muestra significativa y diversa para identificar el verdadero efecto de cada variable sobre el precio de un bien. Otra limitación consiste en que solo pudimos utilizar precios de arte de subastas, ya que esta es la única fuente completa de datos sobre precios de arte que está disponible públicamente. Estas dos limitaciones son compartidas por todos los estudios que utilizan el modelo de precios hedónico.

Nuestros resultados tienen aplicaciones prácticas para coleccionistas e inversores de arte, así como también para artistas, galerías y, en general, para todo el ecosistema del mercado del arte. Los atributos de riesgo y retorno de las diversas expresiones de un artista pueden ser diferentes, por lo que tiene sentido analizar cada una de ellas individualmente, así como sus correlaciones con las otras expresiones artísticas y con las inversiones tradicionales y otras alternativas.

El mercado del arte forma parte de lo que se conoce como “economía naranja” (también conocida como Economía Creativa). Según el Banco Mundial, el valor económico del sector creativo no es bien conocido ni apreciado, a pesar de que las actividades culturales, creativas y artísticas son vitales para nuestra sensación de bienestar.

Hasta donde hemos podido comprobar, este es el primer artículo que compara el desempeño financiero de pinturas, dibujos y esculturas para el caso de un artista específico. Elegimos a Botero por tres razones. En primer lugar, es el artista vivo latinoamericano que ha alcanzado los mayores niveles de ventas internacionales. En segundo lugar, Botero ha trabajado extensamente en diversas expresiones artísticas (óleos, dibujos sobre distintos materiales y esculturas) a lo largo de su vida, característica que resulta fundamental para poder realizar nuestro estudio. En tercer lugar, existe un largo historial de ventas en subasta de cada una de las expresiones artísticas de Botero.

Customer lifetime value (CLV) is one of the key indicators to measure the success or health of an organization. How can an organization assess the organization's customers' lifetime value (LTV) and offer relevant strategies to retain prospective and profitable customers? This study offers an integrated view of different methods for calculating CLVs for both loyalty members and non-membership customers.

This study outlines eleven methods for calculating CLV considering (1) the deterministic aspect of NPV (Net present value) models in both finite and infinite timespans, (2) the geometric pattern and (3) the probabilistic aspect of parameter estimates through simulation modeling along with (4) the migration models for including “the probability that customers will return in the future” as a key input for CLV calculation.

The CLV models are validated in the context of complementary and alternative medicine (CAM)in the healthcare industry. The results show that understanding CLV can help the organization develop strategies to retain valuable customers while maintaining profit margins.

The integrated CLV models provide an overview of the mathematical estimation of LTVs depending on the nature of the customers and the business circumstances and can be applied to other business settings.

The purpose of this study is to establish a novel airfoil icing prediction model using deep learning with geometrical constraints, called geometrical constraints enhancement neural networks, to improve the prediction accuracy compared to the non-geometrical constraints model.

The model is developed with flight velocity, ambient temperature, liquid water content, median volumetric diameter and icing time taken as inputs and icing thickness given as outputs. To enhance the icing prediction accuracy, the model involves geometrical constraints into the loss function. Then the model is trained according to icing samples of 2D NACA0012 airfoil acquired by numerical simulation.

The results show that the involvement of geometrical constraints effectively enhances the prediction accuracy of ice shape, by weakening the appearance of fluctuation features. After training, the airfoil icing prediction model can be used for quickly predicting airfoil icing.

This work involves geometrical constraints in airfoil icing prediction model. The proposed model has reasonable capability in the fast assessment of aircraft icing.