Mengxi Yang, Jie Guo, Lei Zhu, Huijie Zhu, Xia Song, Hui Zhang and Tianxiang Xu
Objectively evaluating the fairness of the algorithm, exploring in specific scenarios combined with scenario characteristics and constructing the algorithm fairness evaluation…
Abstract
Purpose
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.
Design/methodology/approach
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.
Findings
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.
Research limitations/implications
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.
Practical implications
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.
Social implications
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.
Originality/value
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.
Details
Keywords
Guo Chen, Jiabin Peng, Tianxiang Xu and Lu Xiao
Problem-solving” is the most crucial key insight of scientific research. This study focuses on constructing the “problem-solving” knowledge graph of scientific domains by…
Abstract
Purpose
Problem-solving” is the most crucial key insight of scientific research. This study focuses on constructing the “problem-solving” knowledge graph of scientific domains by extracting four entity relation types: problem-solving, problem hierarchy, solution hierarchy and association.
Design/methodology/approach
This paper presents a low-cost method for identifying these relationships in scientific papers based on word analogy. The problem-solving and hierarchical relations are represented as offset vectors of the head and tail entities and then classified by referencing a small set of predefined entity relations.
Findings
This paper presents an experiment with artificial intelligence papers from the Web of Science and achieved good performance. The F1 scores of entity relation types problem hierarchy, problem-solving and solution hierarchy, which were 0.823, 0.815 and 0.748, respectively. This paper used computer vision as an example to demonstrate the application of the extracted relations in constructing domain knowledge graphs and revealing historical research trends.
Originality/value
This paper uses an approach that is highly efficient and has a good generalization ability. Instead of relying on a large-scale manually annotated corpus, it only requires a small set of entity relations that can be easily extracted from external knowledge resources.
Details
Keywords
Cuiping Kang, Gang Wang, Min Shi and Fei Sun
This paper aims to explore the developing trend of higher pedagogy, to promote the research of higher pedagogy to be more canonical and scientific and to improve the higher…
Abstract
Purpose
This paper aims to explore the developing trend of higher pedagogy, to promote the research of higher pedagogy to be more canonical and scientific and to improve the higher education theory.
Design/methodology/approach
The utility research uses a method of quantitative study, namely “content analysis”, to estimate and analyze the higher education theory literature on ten dimensionalities which include theme, author, abstract, keywords, subject, proposing of the issue, definition of key terms, research methods, conclusion, reference and annotations from 1996 to 2006 in China.
Findings
The analysis of the selected 250 academic theses and reports in the field of higher education shows that academic research and theoretical standard have been improved, meanwhile academic criterion have been formed by degrees in higher pedagogy within ten years. At the same time, there are still some problems in the papers and reports the authors have selected such as title, key words, proposing of the issue, researching method and conclusion.
Originality/value
This paper sums up the trend of research on higher education in China for the past ten years, and points out the problems in this trend and then proposes ways to improve the research of higher education in China.
Details
Keywords
Jie Jian, Milin Wang, Lvcheng Li, Jiafu Su and Tianxiang Huang
Selecting suitable and competent partners is an important prerequisite to improve the performance of collaborative product innovation (CPI). The purpose of this paper is to…
Abstract
Purpose
Selecting suitable and competent partners is an important prerequisite to improve the performance of collaborative product innovation (CPI). The purpose of this paper is to propose an integrated multi-criteria approach and a decision optimization model of partner selection for CPI from the perspective of knowledge collaboration.
Design/methodology/approach
First, the criteria for partner selection are presented, considering comprehensively the knowledge matching degree of the candidates, the knowledge collaborative performance among the candidates, and the overall expected revenue of the CPI alliance. Then, a quantitative method based on the vector space model and the synergetic matrix method is proposed to obtain a comprehensive performance of candidates. Furthermore, a multi-objective optimization model is developed to select desirable partners. Considering the model is a NP-hard problem, a non-dominated sorting genetic algorithm II is developed to solve the multi-objective optimization model of partner selection.
Findings
A real case is analyzed to verify the feasibility and validity of the proposed model. The findings show that the proposed model can efficiently select excellent partners with the desired comprehensive attributes for the formation of a CPI alliance.
Originality/value
Theoretically, a novel method and approach to partner selection for CPI alliances from a knowledge collaboration perspective is proposed in this study. In practice, this paper also provides companies with a decision support and reference for partner selection in CPI alliances establishment.
Details
Keywords
This paper aims to collect and compile the historical data of Guanfu Salt Farm, officially built by the Song Dynasty (960–1279) within modern Hong Kong territories, to reconstruct…
Abstract
Purpose
This paper aims to collect and compile the historical data of Guanfu Salt Farm, officially built by the Song Dynasty (960–1279) within modern Hong Kong territories, to reconstruct its history for the reflection of Hong Kong society of the time.
Design/methodology/approach
This paper is largely based on identification and analysis of historical documents, including keyword search on electronic databases and verification with the original sources, with reference to archaeological findings when necessary.
Findings
This paper reconstructs the history of Guanfu Salt Farm based on documentary sources with reference to archaeological findings. English translation of Chinese sources is also provided when necessary.
Originality/value
There has been an absence of systematic compilation of historical data of Hong Kong during the Song Dynasty, which are limited in quantity and scattered across different sources. This paper seeks to fill the vacuum of knowledge about pre-colonial Hong Kong, with a more comprehensive reconstruction of the history of Guanfu Salt Farm.
Details
Keywords
Buffer operators can be utilized to improve the smooth degree of the raw data sequence, and to increase the simulation accuracy of the model. The purpose of this paper is to…
Abstract
Purpose
Buffer operators can be utilized to improve the smooth degree of the raw data sequence, and to increase the simulation accuracy of the model. The purpose of this paper is to analyze the cause of increase in the simulation accuracy of the buffer operator.
Design/methodology/approach
This paper probed into the modeling mechanism of several typical buffer operators such as the arithmetic buffer operators, the buffer operators with monotonic function and weighted buffer operators. The paper also gives an example of the buffer operator sequence.
Findings
The results indicate that after applying an infinite buffer operator, whether the authors adopt a weakening buffer operator or a strengthen buffer operator, the raw sequence can be changed into a constant sequence. Because the discrete GM(1,1) model can completely simulate constant sequence, the simulation accuracy is 100 percent. Because the discrete GM(1,1) model is the accurate form of the GM(1,1) model, after applying an infinite buffer operator, the GM(1,1) model can have a very high simulation accuracy. The buffer operator model can increase the simulation accuracy of both the GM(1,1) model and the discrete GM(1,1) model.
Originality/value
The paper analyses the cause of increasing simulation accuracy of the buffer operator model. The paper may indicate that possible results can be studied in the future. All the buffer operator models have similar properties. After applying an infinite buffer operator, the raw sequence can be changed into a constant sequence. A fixed-point axiom may be the basic cause.
Details
Keywords
Tianxiang Yao and Wenrong Cheng
The purpose of this paper is to find a method that has high precision to forecast the energy consumption of China’s manufacturing industry. The authors hope the predicted data can…
Abstract
Purpose
The purpose of this paper is to find a method that has high precision to forecast the energy consumption of China’s manufacturing industry. The authors hope the predicted data can provide references to the formulation of government’s energy strategy and the sustained growth of economy in China.
Design/methodology/approach
First, the authors respectively make use of regression prediction model and grey system theory GM(1,1) model to construct single model based the data of 2001-2010, analyze the advantages and disadvantages of single prediction models. The authors use the data of 2011 and 2012 to test the model. Second, the authors propose combination forecasting model of manufacturing’s energy consumption in China by using standard variance to allocate the weight. Finally, this model is applied to forecast China’s manufacturing energy consumption during 2013-2016.
Findings
The result shows that the combination model is a better one with higher accuracy; the authors can take the model as an effective tool to predict manufacturing’s energy consumption in China. And the energy consumption of China’s manufacturing industry continued to show a steady incremental trend.
Originality/value
This method takes full advantages of the effective information reflected by the single model and improves the prediction accuracy.
Details
Keywords
Tianxiang Li, Wusheng Yu, Tomas Baležentis, Jing Zhu and Yueqing Ji
The purpose of this paper is to identify the effects of recent demographic transition and rising labor costs on agricultural production structure and pattern in China during…
Abstract
Purpose
The purpose of this paper is to identify the effects of recent demographic transition and rising labor costs on agricultural production structure and pattern in China during 1998-2012.
Design/methodology/approach
The authors, first, theoretically discuss the effects of changing relative input prices due to rising labor cost on producers’ decisions regarding input mix (substitution effect), output level, and product quality (output effect). A logarithmic mean Divisia index decomposition method is then applied to empirically identify these effects at aggregated levels, followed by an analysis based on the visualization of land use indicators on changing cropping patterns across Chinese provinces.
Findings
The authors find that tightened effective agricultural labor supply and rises in rural labor costs are associated with divergent changes in input mixes and output choices across products. Producers of land-intensive products focusing more on input mix adjustment, while those of labor-intensive products seem to more likely to adjust output choices. Producers’ adaption strategies also varied across Chinese provinces due to natural conditions, leading to shifts and concentrations in the regional distribution of agricultural products, with lower-value bulk products concentrating in the plain areas, whereas higher-value horticulture products increasingly prevailing in sloped areas.
Originality/value
This paper illustrates how adjustments in input mixes and output choice in Chinese agriculture counteracted disadvantages caused by rising labor costs and how such adjustments are product and region specific. Based on these observations, implications regarding further innovations in production technology and institutional arrangements needed within China’s agricultural sector are highlighted in the paper.
Details
Keywords
The purpose of this study is to explore how nationalistic appeals may affect consumers’ perception and purchasing of targeted brands. Qualitative historical data from old China…
Abstract
Purpose
The purpose of this study is to explore how nationalistic appeals may affect consumers’ perception and purchasing of targeted brands. Qualitative historical data from old China (1900–1949) reveal that social movement groups can adopt nationalistic appeals assisted by meaning framing – defined as a creative interpretation of symbols, designs, behaviors, social events and cultural identities to serve social and political goals – to shape consumers’ attitudes toward foreign brands. After examining the mechanisms and processes underlying consumer boycotts from 1900 to 1949, the responsive strategies of affected foreign companies are illustrated.
Design/methodology/approach
Critical historical research method is applied to historical data and historical “traces” from China’s corporate documents, memoirs, posters, advertisements, newspapers and secondhand sources documenting Chinese boycotts from 1900 to 1949.
Findings
Consumers may pursue interests beyond economic interests. Nationalistic appeals can mobilize consumer boycotts against foreign brands that were perceived to support or relate to targeted countries. Political framing of certain events shapes consumers’ perceptions and concomitant brand choices.
Research limitations/implications
Although differences between historical and current contexts may require tailoring past marketing strategies to current conditions, past strategies can inform current and future strategies.
Practical implications
Strategies adopted by foreign companies in old China (1900–1949) can help contemporary companies design effective marketing strategies for a hostile marketplace infused with nationalistic appeals and competing interests.
Social implications
Although local companies can adopt economic or political nationalism to realize their economic goals, it represents a double-edged sword that can harm national brands.
Originality/value
A historical analysis of nationalistic business appeals in pre-1949 China can inform the counterstrategies modern companies adopt to overcome consumer boycotts.
Details
Keywords
Yang Li and Tianxiang Lan
This paper aims to employ a multivariate nonlinear regression analysis to establish a predictive model for the final fracture area, while accounting for the impact of individual…
Abstract
Purpose
This paper aims to employ a multivariate nonlinear regression analysis to establish a predictive model for the final fracture area, while accounting for the impact of individual parameters.
Design/methodology/approach
This analysis is based on the numerical simulation data obtained, using the hybrid finite element–discrete element (FE–DE) method. The forecasting model was compared with the numerical results and the accuracy of the model was evaluated by the root mean square (RMS) and the RMS error, the mean absolute error and the mean absolute percentage error.
Findings
The multivariate nonlinear regression model can accurately predict the nonlinear relationships between injection rate, leakoff coefficient, elastic modulus, permeability, Poisson’s ratio, pore pressure and final fracture area. The regression equations obtained from the Newton iteration of the least squares method are strong in terms of the fit to the six sensitive parameters, and the model follow essentially the same trend with the numerical simulation data, with no systematic divergence detected. Least absolutely deviation has a significantly weaker performance than the least squares method. The percentage contribution of sensitive parameters to the final fracture area is available from the simulation results and forecast model. Injection rate, leakoff coefficient, permeability, elastic modulus, pore pressure and Poisson’s ratio contribute 43.4%, −19.4%, 24.8%, −19.2%, −21.3% and 10.1% to the final fracture area, respectively, as they increased gradually. In summary, (1) the fluid injection rate has the greatest influence on the final fracture area. (2)The multivariate nonlinear regression equation was optimally obtained after 59 iterations of the least squares-based Newton method and 27 derivative evaluations, with a decidability coefficient R2 = 0.711 representing the model reliability and the regression equations fit the four parameters of leakoff coefficient, permeability, elastic modulus and pore pressure very satisfactorily. The models follow essentially the identical trend with the numerical simulation data and there is no systematic divergence. The least absolute deviation has a significantly weaker fit than the least squares method. (3)The nonlinear forecasting model of physical parameters of hydraulic fracturing established in this paper can be applied as a standard for optimizing the fracturing strategy and predicting the fracturing efficiency in situ field and numerical simulation. Its effectiveness can be trained and optimized by experimental and simulation data, and taking into account more basic data and establishing regression equations, containing more fracturing parameters will be the further research interests.
Originality/value
The nonlinear forecasting model of physical parameters of hydraulic fracturing established in this paper can be applied as a standard for optimizing the fracturing strategy and predicting the fracturing efficiency in situ field and numerical simulation. Its effectiveness can be trained and optimized by experimental and simulation data, and taking into account more basic data and establishing regression equations, containing more fracturing parameters will be the further research interests.