Template-Type: ReDIF-Article 1.0 Author-Name: Jie Liu Author-X-Name-First: Jie Author-X-Name-Last: Liu Author-Name: Ning Wang Author-X-Name-First: Ning Author-X-Name-Last: Wang Title: Research on precise employment data analysis and practice of university graduates based on web system implementation Abstract: Based on big data technology and its application, this paper outlines the current problems of college employment, gives specific strategies for college employment services, and designs the main framework of the college student employment information service platform in the new era. To this end, a web-based employment management system for college graduates is designed. The information sharing platform is used for information collection and classification, data induction, mining and analysis, intelligent classification guidance for graduate resumes, and vocational assessment and occupational assessment. Skill assessment, accurately matching the job information of graduates, helping graduates to achieve precise employment. At the same time, we use big data technology to analyse the employment process of students, and further guide them to find employment according to the data analysis results. Journal: Int. J. of Data Science Pages: 138-151 Issue: 2 Volume: 8 Year: 2023 Keywords: web; management system; big data; employment service management platform; graduates. File-URL: http://www.inderscience.com/link.php?id=131426 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:8:y:2023:i:2:p:138-151 Template-Type: ReDIF-Article 1.0 Author-Name: Shinichi Murata Author-X-Name-First: Shinichi Author-X-Name-Last: Murata Author-Name: Hiroshi Morita Author-X-Name-First: Hiroshi Author-X-Name-Last: Morita Title: Feature analysis applying clustering and optimisation methods to Mahalanobis-Taguchi method Abstract: While data analysis is important in various corporate activities, it is often the case that a company's data analysis is not well-conducted. There are two main reasons for this: the lack of teacher data and the increasingly complicated nature of the data to be analysed, which makes it difficult to judge the appropriate analysis unit/group and to select the appropriate items to be used for the analysis. In response, we propose a data analysis approach that combines a clustering and a stochastic optimisation model with the Mahalanobis-Taguchi method, making it possible to automatically determine the group of data to be analysed and the items of data to be used, and to extract features from the data. The proposed approach enables data analysis with a single correct label and eliminates tasks that require higher-level skills (such as feature selection). The effectiveness of the proposed method is verified using recorded TV data. Journal: Int. J. of Data Science Pages: 89-103 Issue: 2 Volume: 8 Year: 2023 Keywords: Mahalanobis-Taguchi method; clustering; x-means; k-means; optimisation method; operations research; genetic algorithm; feature selection; data analysis; recorded TV data. File-URL: http://www.inderscience.com/link.php?id=131427 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:8:y:2023:i:2:p:89-103 Template-Type: ReDIF-Article 1.0 Author-Name: Xianrong Zheng Author-X-Name-First: Xianrong Author-X-Name-Last: Zheng Title: Cloud service quality: a research roadmap Abstract: As cloud services become increasingly popular, cloud providers compete to offer the same or similar services over the internet. Quality of Service (QoS), which describes how well a cloud service is performed, will be more important. QoS refers to nonfunctional properties of cloud services, and is an important differentiator among functionally equivalent cloud services. As a result, how to evaluate and assure QoS becomes important in both IT and business disciplines. This paper argues for QoS evaluation and assurance in cloud services. It reviews the state-of-the-art, reports our latest work, and discusses future research directions and challenges on the two topics. The paper proposes a new benchmark suite for measuring cloud services and a new economic method for allocating cloud resources. The benchmark suite can provide comparable QoS data for cloud services. The economic method can meet users' QoS needs while minimising resources consumed for cloud services. Journal: Int. J. of Data Science Pages: 124-137 Issue: 2 Volume: 8 Year: 2023 Keywords: cloud computing; QoS; cloud benchmark; resource allocation. File-URL: http://www.inderscience.com/link.php?id=131428 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:8:y:2023:i:2:p:124-137 Template-Type: ReDIF-Article 1.0 Author-Name: Cong Li Author-X-Name-First: Cong Author-X-Name-Last: Li Title: The construction of smart city information service system in the era of big data Abstract: To improve the overall quality and efficiency of urban and rural construction, build a smart city information service system in the context of big data. This paper studies the problems such as improper construction planning in the construction of the national smart city information service system. According to the construction goals, build the smart city information service system under the background of big data, and integrate the smart city information under big data by using data clustering algorithm. The constructed smart city has high quality information services and high public recognition. In the construction of Jiuhua National Economic Development Zone's smart city, after applying the information service system built by the research, the satisfaction of the smart city's information service reaches 99.9%, which indicates that the smart city information service system built by this research has a high quality of smart city information service and public recognition. Journal: Int. J. of Data Science Pages: 104-123 Issue: 2 Volume: 8 Year: 2023 Keywords: Big data era; smart city; information service; PEST analysis; text analysis. File-URL: http://www.inderscience.com/link.php?id=131429 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:8:y:2023:i:2:p:104-123 Template-Type: ReDIF-Article 1.0 Author-Name: Tianming Zu Author-X-Name-First: Tianming Author-X-Name-Last: Zu Title: Application of adaptive back propagation neural network algorithm in vehicle scheduling of logistics enterprises Abstract: With the rapid development of modern logistics, customers have higher and higher requirements for order delivery. With the increasing logistics pressure, the logistics vehicle scheduling problem (VRP) has become the focus of the industry to ensure the timeliness and smoothness of logistics. Based on this, a vehicle scheduling model based on self-adaptation back propagation (SABP) is constructed. The results show that the prediction accuracy rate of the model established in the research is 96.5%, which is much higher than the prediction accuracy rate of the traditional support vector machine (SVM) model and the traditional BP neural network model. The SABP model can reach the expected accuracy after 208 iterations, and the number of iterations is much lower than the other two models. The experiment shows that the model can accurately predict the shortest path and complete the distribution with the lowest cost. Journal: Int. J. of Data Science Pages: 152-168 Issue: 2 Volume: 8 Year: 2023 Keywords: BP neural algorithm; adaptive; logistics enterprise; vehicle scheduling; least square method; grey relational analysis; travelling salesman problems; route optimisation. File-URL: http://www.inderscience.com/link.php?id=131430 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:8:y:2023:i:2:p:152-168 Template-Type: ReDIF-Article 1.0 Author-Name: Youqin Pan Author-X-Name-First: Youqin Author-X-Name-Last: Pan Author-Name: Jian Gu Author-X-Name-First: Jian Author-X-Name-Last: Gu Author-Name: David Goodof Author-X-Name-First: David Author-X-Name-Last: Goodof Title: The importance of trade openness and logistics performance in economic growth: a Lasso-based approach Abstract: This study explores the impacts of logistics performance and trade openness on economic growth. The least absolute shrinkage and selection operator (Lasso) regression models were applied to perform variable selection for feature variables using logistics performance index (LPI), gross domestic product (GDP), and trade openness (OP) during the periods when LPI data were available from 2010 to 2018. The results reveal that infrastructure, timeliness, and trade openness are major factors that affect a country's economic growth. Moreover, interactive terms between trade openness and specific logistics indicators such as customs, infrastructure, and timeliness are statistically significant. The main policy implication is that continuous improvement in logistics infrastructure and timeliness leads to positive economic growth. Additionally, trade openness needs to be factored into logistics decision-making to better boost economic development because greater trade openness may not lead to economic growth due to negative interactive effects. Journal: Int. J. of Data Science Pages: 275-294 Issue: 4 Volume: 8 Year: 2023 Keywords: LPI index; Lasso; trade openness; infrastructure; logistics performance; timeliness. File-URL: http://www.inderscience.com/link.php?id=134547 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:8:y:2023:i:4:p:275-294 Template-Type: ReDIF-Article 1.0 Author-Name: Vikas Khare Author-X-Name-First: Vikas Author-X-Name-Last: Khare Title: Performance assessment of the Mumbai Indians and Royal Challengers Bangalore in the Indian Premier League by computational data analysis Abstract: The Indian Premier League (IPL) is a professional Twenty20 cricket league in India that features eight teams from eight different cities. The Mumbai Indians (MI) and Royal Challengers Bangalore (RCB) are an IPL franchise cricket team based in Mumbai and Bangalore, respectively. This paper shows the performance assessment of the Mumbai Indians and royal challengers by the NCSS tool-based process of data analysis. The main objective of the comparison of performance assessments of the Mumbai Indians and RCB is that both teams spent almost the same amount of money on their players and also have the same level of players, but there are many differences between the performances of both teams. All the statistical and descriptive analysis shows that MI is a much better team compared to RCB. Results show that in the future, the win% of MI will be approximately 62% and the win% of RCB will be only 46%. Journal: Int. J. of Data Science Pages: 295-329 Issue: 4 Volume: 8 Year: 2023 Keywords: NCSS tool; regression analysis; Michaelis-Menten concept; non-linear regression; data analysis; descriptive statistics; cricket. File-URL: http://www.inderscience.com/link.php?id=134550 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:8:y:2023:i:4:p:295-329 Template-Type: ReDIF-Article 1.0 Author-Name: Gaoxiu Liu Author-X-Name-First: Gaoxiu Author-X-Name-Last: Liu Author-Name: Yuqing Liu Author-X-Name-First: Yuqing Author-X-Name-Last: Liu Author-Name: Wanqing Lv Author-X-Name-First: Wanqing Author-X-Name-Last: Lv Title: Analysis of the effectiveness of sterilised intervention policies in China Abstract: With the change in the scale of China's foreign exchange reserves, in order to withdraw the base currency and reduce the expansion of the money supply and inflationary pressure caused by the increase in foreign exchange reserves, the scale of sterilised intervention by the central bank has also expanded. In this paper, the sterilisation coefficient and the offset coefficient are used to analyse the effectiveness of the sterilised intervention policy in China. The results show that the change in the scale of foreign exchange reserves has caused great trouble for the implementation of monetary policy in China. However, due to the reasonable use of sterilised intervention policy and sterilisation tools, the implementation effect of the sterilisation policy is better, but at the same time, the offsetting effect of changes in foreign exchange reserves on China's monetary policy is also expanding. Journal: Int. J. of Data Science Pages: 330-351 Issue: 4 Volume: 8 Year: 2023 Keywords: foreign exchange reserve; sterilised intervention; sterilisation coefficient; offset coefficient; central bank; monetary policy. File-URL: http://www.inderscience.com/link.php?id=134558 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:8:y:2023:i:4:p:330-351 Template-Type: ReDIF-Article 1.0 Author-Name: Shenghu Fan Author-X-Name-First: Shenghu Author-X-Name-Last: Fan Title: A few-shot image classification method based on feature cross-attention Abstract: In neural networks, obtaining complete position information from image feature extraction is a difficult task. In order to overcome this issue, an embedded feature cross-attention network (CAN) is proposed in this paper to extract useful key information from a small sample. Firstly, channel and spatial features are generated using global pooling of the channel and spatial dimensions, respectively. Secondly, an attention map is generated by intersecting the channel and spatial features with the original features. Next, the channel and space-crossing attention maps are combined to produce fused feature information. Finally, the fusion features are embedded into the neural network architecture for end-to-end training. To evaluate its effectiveness, the proposed feature cross-attention module was embedded in a prototype network of classical and relational networks for few-shot learning during the experiment. The mean squared error loss method trained the relational attention model to transform the image classification problem into a classification problem with a label space of {0,1}. The experimental results demonstrate and validate that the network embedded with the proposed feature attention module outperforms the original network. Journal: Int. J. of Data Science Pages: 361-374 Issue: 4 Volume: 8 Year: 2023 Keywords: attention model; CAN; cross-attention network; few-shot classification; Siamese network; feature extraction; attention module; global average pooling; PAN; prototype attention network. File-URL: http://www.inderscience.com/link.php?id=134564 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:8:y:2023:i:4:p:361-374 Template-Type: ReDIF-Article 1.0 Author-Name: Zhaoqiong Qin Author-X-Name-First: Zhaoqiong Author-X-Name-Last: Qin Title: Extant literature and perspectives in distribution channel models Abstract: This study identifies the gaps between academia and the business world based on the detailed literature on distribution channel models from the perspectives of the number of suppliers and retailers, channel differences, and research techniques. Following that, three main recommendations are shown for future research in the distribution channel models: 1) channel competition in the scenario that many suppliers and many retailers are involved in multiple channels; 2) feasibility of the multiple-channel coexistence; and 3) the threshold on the number of suppliers or retailers entering the given markets to be profitable. There are very limited preliminary results from the current literature for the proposed recommendations. Overall, it is only a direction and requires researchers' thorough investigation before starting the research. Journal: Int. J. of Data Science Pages: 352-360 Issue: 4 Volume: 8 Year: 2023 Keywords: distribution channel; model; literature; research technique; channel difference; number of suppliers; number of retailers. File-URL: http://www.inderscience.com/link.php?id=134565 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:8:y:2023:i:4:p:352-360 Template-Type: ReDIF-Article 1.0 Author-Name: Shraddha Kumar Author-X-Name-First: Shraddha Author-X-Name-Last: Kumar Author-Name: Anuradha Purohit Author-X-Name-First: Anuradha Author-X-Name-Last: Purohit Author-Name: Sunita Varma Author-X-Name-First: Sunita Author-X-Name-Last: Varma Title: Review of spectral clustering algorithms used in proteomics Abstract: Tandem mass spectrometry (MS/MS) generates a large number of spectra showing the signal intensity of detected ions as a function of mass-to-charge ratio. Spectral clustering in proteomics is a powerful but under-utilised technique. Based on the similarity of spectra, the spectral clustering algorithms systematically and unerringly classify large numbers of spectra, such that all spectra in a given cluster belong to the same peptide. The data points in the spectral clustering approach are connected and do not require having convex boundaries. Spectral clustering therefore reduces the running time and computation requirements of spectral library and database searches. It enhances peptide identification process and has fuelled the development of many new proteomics algorithms recently. The goal of this review is to provide a clear overview of the most popular spectral clustering algorithms used in proteomics. It describes a systematic analysis of these spectral clustering algorithms, evaluating the benefits and limitations of each approach. Journal: Int. J. of Data Science Pages: 16-38 Issue: 1 Volume: 8 Year: 2023 Keywords: proteomics; tandem mass spectrometry; spectral clustering; consensus spectrum; scoring function; mass spectra; data points; spectral similarity; cluster purity; spectral library; normalised dot product. File-URL: http://www.inderscience.com/link.php?id=129449 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:8:y:2023:i:1:p:16-38 Template-Type: ReDIF-Article 1.0 Author-Name: Lijuan Xiang Author-X-Name-First: Lijuan Author-X-Name-Last: Xiang Title: Study on compensation mechanism for regional ecological protection under the background of ecological civilisation Abstract: To improve the effect of regional ecological protection, research on the compensation mechanism for regional ecological protection under the background of ecological civilisation is proposed. Firstly, the connotation of ecological civilisation and the basic process of ecological compensation are expounded to make the whole compensation process clearer; secondly, the ecological footprint is innovatively used as the evaluation index of regional ecological protection compensation, the ecological carrying capacity is calculated, and a three-dimensional ecological footprint model (EFM) is established; Finally, introduce the principle of ecological compensation priority, establish an ecological protection compensation model, calculate the amount of ecological protection compensation, and realise regional ecological protection compensation under the background of ecological civilisation. The experimental results show that, compared with the traditional compensation methods, the compensation for ecological protection amount structure of this method is basically consistent with the actual results, and the ECC and compensation coverage have been improved. Journal: Int. J. of Data Science Pages: 52-68 Issue: 1 Volume: 8 Year: 2023 Keywords: ecological civilisation; regional ecological protection; compensation mechanism; 3D EFM; regional evaluation indicators; carrying capacity; ECC. File-URL: http://www.inderscience.com/link.php?id=129455 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:8:y:2023:i:1:p:52-68 Template-Type: ReDIF-Article 1.0 Author-Name: Wenya Li Author-X-Name-First: Wenya Author-X-Name-Last: Li Title: Texture feature extraction of a landscape design image based on the contour wave transform Abstract: In order to optimise the landscape design, this study takes the contour wave transform as the core research object, deeply explores its filter setting and action mechanism, and applies it to the extraction of image texture features of landscape design. The results show that when the number of degraded distortion trend feature points is only 100, the feature extraction accuracy of the algorithm has almost reached 90% and continues to improve with the increase of the number of feature points, which is always much higher than other algorithms. This shows that the texture feature extraction of the landscape design image based on the contour wave transform has strong robustness. The algorithm has good application effects on the recognition and extraction of target image features and the evaluation and analysis of image quality. When mixing all image distortion types, it can obtain better extraction and evaluation results. Journal: Int. J. of Data Science Pages: 39-51 Issue: 1 Volume: 8 Year: 2023 Keywords: contour wave transform; gardens; landscape design; image; texture features; extract. File-URL: http://www.inderscience.com/link.php?id=129456 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:8:y:2023:i:1:p:39-51 Template-Type: ReDIF-Article 1.0 Author-Name: Caihong Feng Author-X-Name-First: Caihong Author-X-Name-Last: Feng Title: Reform strategies of public government departments in the era of cultural innovation Abstract: In the background of cultural innovation and with the rapid development of various new media technologies, the acceleration of information dissemination will affect the smooth development of the work of government departments. Therefore, taking China as an example, starting from the overall framework of public government sector governance and its power structure, this paper analyses the significance, value orientation and goal of public government sector reform. In view of many deficiencies in the government's response to the reform of public government departments in the era of cultural innovation, this paper puts forward the principles and strategies of the reform of public government departments. Through determining the list of public service institutions of public government departments, innovating the public service mechanism, improving the openness and transparency of government information, and other ways, it is expected to promote the reform of public government departments and improve the effectiveness of government management. Journal: Int. J. of Data Science Pages: 69-88 Issue: 1 Volume: 8 Year: 2023 Keywords: cultural innovation era; public government; balanced scorecard; big data capability model; governance structure; power structure; reform strategy; management efficiency. File-URL: http://www.inderscience.com/link.php?id=129457 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:8:y:2023:i:1:p:69-88 Template-Type: ReDIF-Article 1.0 Author-Name: Jinyun Jiang Author-X-Name-First: Jinyun Author-X-Name-Last: Jiang Author-Name: Shiyi Ying Author-X-Name-First: Shiyi Author-X-Name-Last: Ying Author-Name: Wanxin Fu Author-X-Name-First: Wanxin Author-X-Name-Last: Fu Author-Name: Xiaoliang Jiang Author-X-Name-First: Xiaoliang Author-X-Name-Last: Jiang Title: Structure design and system implementation of a supermarket shopping robot based on deep learning Abstract: To enhance the operating efficiency of supermarkets, reduce their labour costs, and satisfy people's shopping experiences, we present the design and implementation of a supermarket shopping robot based on deep learning. Firstly, the robot adopts high-performance STM32F407 as its main control chip and is powered by 4 DC motors. It relies on 12 grey-scale sensors, gyroscopes and other devices for path planning. Through the infrared detection module, detect whether there are goods in the cargo window, and use the manipulator to accurately grasp and place the goods. Secondly, design a shopping cart to replace the manual cart to maintain the robot's control of the shopping cart during the shopping process. Finally, the AlexNet network is used as the feature extractor to realise the rapid identification of the target cargos. The experimental results show that under the simulation of the real supermarket environment, the designed robot runs flexibly, stably and reliably, and can well complete the purchase and supply of commodities, which is in line with the development trend of artificial intelligence. Journal: Int. J. of Data Science Pages: 1-15 Issue: 1 Volume: 8 Year: 2023 Keywords: supermarket shopping robot; deep learning; single-chip microcomputer; recognition; AlexNet. File-URL: http://www.inderscience.com/link.php?id=129458 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:8:y:2023:i:1:p:1-15 Template-Type: ReDIF-Article 1.0 Author-Name: Neeraj Kumar Bharti Author-X-Name-First: Neeraj Kumar Author-X-Name-Last: Bharti Author-Name: Vijay Verma Author-X-Name-First: Vijay Author-X-Name-Last: Verma Title: Slope one collaborative recommendations: a survey Abstract: Collaborative filtering (CF) is a traditional and popular technique in the recommendation system (RS) paradigm. Notably, one specific form of item-based collaborative filtering (IBCF), known as the slope one algorithm, deals with data sparsity in many different ways. Slope one algorithms are simple; therefore, their implementations are more straightforward than other complicated IBCF approaches. This work summarises the state-of-the-art techniques for slope one recommendations. Various slope one predictors are analysed and compared with each other along with their pros and cons. Several experiments have been performed using different datasets such as MovieLens-100k, MovieLens-1M, and Filmtrust. Finally, the weighted slope one predictor is compared with the basic IBCF using mean absolute error (MAE) and root mean squared error (RMSE) metrics. Empirical values of MAE and RMSE demonstrate that the slope one predictors provide the almost same accuracy as obtained from other complex and computationally expensive methods. Journal: Int. J. of Data Science Pages: 240-257 Issue: 3 Volume: 8 Year: 2023 Keywords: recommender system; slope one; collaborative filtering; item-based CF; data sparsity. File-URL: http://www.inderscience.com/link.php?id=132284 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:8:y:2023:i:3:p:240-257 Template-Type: ReDIF-Article 1.0 Author-Name: Bibi Faheema Luckhoo Author-X-Name-First: Bibi Faheema Author-X-Name-Last: Luckhoo Author-Name: Arshad Ahmud Iqbal Peer Author-X-Name-First: Arshad Ahmud Iqbal Author-X-Name-Last: Peer Title: A DEA-WEI method for ranking universities in the presence of imprecise data Abstract: Ranking universities has become increasingly common in recent years as it is considered a significant source of comparative information for various stakeholders. The three main university rankings differ by methodology and results since different parameters are considered. In this paper, data envelopment analysis (DEA) is used to obtain a unified ranking of universities based on the data of these ranking systems. Due to the absence of input measures in the dataset, DEA-WEI (without explicit input) models are studied. In order to consolidate the classification, the established rankings of the three ranking systems, which are ordinal data, are considered. As such, we suggest a new approach to rank the universities in situations where imprecise data and only output measures are present. Journal: Int. J. of Data Science Pages: 211-239 Issue: 3 Volume: 8 Year: 2023 Keywords: DEA; data envelopment analysis; university rankings; imprecise data; ordinal data; WEI; without explicit inputs. File-URL: http://www.inderscience.com/link.php?id=132285 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:8:y:2023:i:3:p:211-239 Template-Type: ReDIF-Article 1.0 Author-Name: Erio Castagnoli Author-X-Name-First: Erio Author-X-Name-Last: Castagnoli Author-Name: Marzia De Donno Author-X-Name-First: Marzia De Author-X-Name-Last: Donno Author-Name: Gino Favero Author-X-Name-First: Gino Author-X-Name-Last: Favero Author-Name: Paola Modesti Author-X-Name-First: Paola Author-X-Name-Last: Modesti Title: On representation of preferences à la Debreu Abstract: A representation theorem proven by G. Debreu in 1960, although somehow neglected by the literature, implies several deep and unexplored consequences both for Economics and for Decision Theory. This paper focuses on some of them. In particular, possible decompositions of state-dependent utilities à la Debreu (which may equivalently be seen as 'utility-dependent probabilities') are analysed, showing that Debreu's representation is based upon a 'joint' probability/utility function. It is illustrated how Debreu's Theorem can provide a neat geometrical interpretation of Castagnoli and LiCalzi's 'benchmarking' representation of preferences. (Conditional) Certainty Equivalents are defined and studied, and possible implications for attempting representation of incomplete preferences are discussed. Journal: Int. J. of Data Science Pages: 175-194 Issue: 3 Volume: 8 Year: 2023 Keywords: Debreu's theorem; representation of preferences; sure thing principle; state-dependent utility; benchmarking; certainty equivalents; incomplete preferences. File-URL: http://www.inderscience.com/link.php?id=132293 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:8:y:2023:i:3:p:175-194 Template-Type: ReDIF-Article 1.0 Author-Name: Hua Tian Author-X-Name-First: Hua Author-X-Name-Last: Tian Title: Research on the driving mechanism of business model innovation of startups based on big data analysis in the context of digital economy Abstract: In this paper, we use discourse analysis to refine the mechanism of business model innovation based on 100 big data cases. A model of 16 discourse elements in four categories of data, behaviour, attributes and scenarios is obtained, and the relationship paths between the above-mentioned discourse elements and categories are mapped. This paper evaluates the change of business model innovation of the company by using the entropy - mutation level method by selecting the financial data from 2007 to 2020. Therefore, based on the evaluation results, the development of the company's business model in the period of competitive leadership and strategic transformation is divided into three phases for analysis, and corresponding suggestions are made for the innovation of the company's business model accordingly. Journal: Int. J. of Data Science Pages: 195-210 Issue: 3 Volume: 8 Year: 2023 Keywords: digital economy; data analysis; enterprise management; business model innovation; overall stability. File-URL: http://www.inderscience.com/link.php?id=132294 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:8:y:2023:i:3:p:195-210 Template-Type: ReDIF-Article 1.0 Author-Name: Taicheng Wei Author-X-Name-First: Taicheng Author-X-Name-Last: Wei Author-Name: Hao Chen Author-X-Name-First: Hao Author-X-Name-Last: Chen Author-Name: Yuting Ou Author-X-Name-First: Yuting Author-X-Name-Last: Ou Author-Name: Chen Zhang Author-X-Name-First: Chen Author-X-Name-Last: Zhang Author-Name: Haiying Li Author-X-Name-First: Haiying Author-X-Name-Last: Li Author-Name: Yue Huang Author-X-Name-First: Yue Author-X-Name-Last: Huang Author-Name: Yanbing Liu Author-X-Name-First: Yanbing Author-X-Name-Last: Liu Title: Evaluation of cigarette market state based on multi-source data modelling Abstract: Traditional cigarette market forecasting model usually has a low accuracy since it did not take the external data into account. Thus, a random forest was firstly used to extract features of data and rank the importance of influencing factors. Then, different external factors were eliminated, the percentage of reduced model interpretation was demonstrated, and expert feedback was introduced to input evaluation values. After optimising the training RF-LSTM model, the prediction of the whole market sales status were finally constructed, and the historical week cigarette market status evaluation model was also established. The proposed machine learning model had a high prediction accuracy and generalisation based on the local market data in province Guangxi of China. Overall results demonstrated that it can accurately and conveniently evaluate the market status of cigarettes. Journal: Int. J. of Data Science Pages: 258-273 Issue: 3 Volume: 8 Year: 2023 Keywords: multi-source data; cigarette market; evaluation; deep learning; machine learning. File-URL: http://www.inderscience.com/link.php?id=132295 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:8:y:2023:i:3:p:258-273