Deep Learning Based Customer Preferences Analysis in Industry 4.0 Environment

Customer preferences analysis and modelling using deep learning in edge computing environment are critical to enhance customer relationship management that focus on a dynamically changing market place. Existing forecasting methods work well with often seen and linear demand patterns but become less accurate with intermittent demands in the catering industry. In this paper, we introduce a throughput deep learning model for both short-term and long-term demands forecasting aimed at allowing catering businesses to be highly efficient and avoid wastage. Moreover, detailed data collected from a business online booking system in the past three years have been used to train and verify the proposed model. Meanwhile, we carefully analyzed the seasonal conditions as well as past local or national events (event analysis) that could have had critical impact on the sales. The results are compared with the best performing forecast methods Xgboost and autoregressive moving average model (ARMA), and they suggest that the proposed method significantly improves demand forecasting accuracy (up to 80%) for dishes demand along with reduction in associated costs and labor allocation.

A Weighted Statistical Network Modeling Approach to Product Competition Analysis

Statistical network models have been used to study the competition among different products and how product attributes influence customer decisions. However, in existing research using network-based approaches, product competition has been viewed as binary (i.e., whether a relationship exists or not), while in reality, the competition strength may vary among products. In this paper, we model the strength of the product competition by employing a statistical network model, with an emphasis on how product attributes affect which products are considered together and which products are ultimately purchased by customers. We first demonstrate how customers’ considerations and choices can be aggregated as weighted networks. Then, we propose a weighted network modeling approach by extending the valued exponential random graph model to investigate the effects of product features and network structures on product competition relations. The approach that consists of model construction, interpretation, and validation is presented in a step-by-step procedure. Our findings suggest that the weighted network model outperforms commonly used binary network baselines in predicting product competition as well as market share. Also, traditionally when using binary network models to study product competitions and depending on the cutoff values chosen to binarize a network, the resulting estimated customer preferences can be inconsistent. Such inconsistency in interpreting customer preferences is a downside of binary network models but can be well addressed by the proposed weighted network model. Lastly, this paper is the first attempt to study customers’ purchase preferences (i.e., aggregated choice decisions) and car competition (i.e., customers’ co-consideration decisions) together using weighted directed networks.

CUSTOMER INCLINATION ON MOBILE WALLETS WITH REFERENCE TO GOOGLE-PAY AND PAYTM IN BENGALURU CITY

In this cashless economy era, Information and Communication Technology (ICT) plays a vital role in making payments using various payment modes. The mobile wallet app is an innovative technology for avoiding the usage of physical cash. The mobile wallet records all kinds of transactions with a clear payment reference and makes it accountable for tax payments. There are countless reasons for using mobile wallets which makes service providers confused and leads them to offer unattractive features in the wallet apps making the offer as a failure. This paper attempts to collect the data from the mobile wallet users and provide a clear understanding of the reasons for using mobile wallets. Secondly, the customer preferences towards Google Pay and PayTm are analyzed in detail with primary data collected from mobile wallet users to suggest a model for improving the business. This research was conducted to understand the customer's inclination towards the use of mobile wallets.

Relationships between mental workload, job burnout, and organizational commitment

The business environment has becoming exceptionally unsteady and competitive recently. Information technology advancements and ever changing customer preferences has played a substantial role in an increase of the significance of highly productive, committed and loyal employees. These changes bring both advantages and challenges need to be addressed. The more challenges accelerate, the more issues come up to solve in timely manner. For any organizations, not only taking care of the customers but also employees of the organization should be treated equally taking a better care about their psychological and physical health as well as creating a healthy work environment. The objective of the current research is to study correlations of workload, job burnout and organizational commitment in the case of nurses working in the Health Center of Selenge aimag, Mongolia. According to the results, an increase of mental workload nurses by one unit results in job burnout increases by 0.578 (beta) unit and leads to the decrease of the organizational commitment by 0.437 (beta) unit. Moreover, one-unit increase of job burnout leads to decrease of the organizational commitment by 0.301 (beta) unit.

Finance and Innovation Solutions to Implement Investment Programs in Electric-Power Complex of the Russian Federation

Today we observe changes in concepts of organizing power - engineering industry and tariff pricing. While estimating the pressure of sanctions, everybody agrees that the worst damage is caused by finance tools. Therefore, innovation in electric-power sector is started with finance innovation. It is also necessary to bear in mind the future earnings of stakeholders and households that plan to re-orient their investment from oil sector to electric-power engineering. This trend is being discussed right now, though for Russia with its gas reserves and customer preferences the process of investment changes can be rather long. The finance platform in this industry is not fundamental yet. It is possible to start innovation only after accumulating some funds. For instance, it is planned to change elements in the structure of power and fuel potential, to reform technical and technological elements of infrastructure (chat-bots with geographic and product applications, drones, quadrocopters, which can be used for linear and high buildings). In the future it is planned to develop new customer clusters with certain social index. In the article the authors study finance and innovation solutions to implement innovation programs in electricpower complex in conditions of digitalization and imperative indices of investment, though digitalization is called the key anti-ecological factor in this sector.

Learning Personalized Product Recommendations with Customer Disengagement

Problem definition: We study personalized product recommendations on platforms when customers have unknown preferences. Importantly, customers may disengage when offered poor recommendations. Academic/practical relevance: Online platforms often personalize product recommendations using bandit algorithms, which balance an exploration-exploitation trade-off. However, customer disengagement—a salient feature of platforms in practice—introduces a novel challenge because exploration may cause customers to abandon the platform. We propose a novel algorithm that constrains exploration to improve performance. Methodology: We present evidence of customer disengagement using data from a major airline’s ad campaign; this motivates our model of disengagement, where a customer may abandon the platform when offered irrelevant recommendations. We formulate the customer preference learning problem as a generalized linear bandit, with the notable difference that the customer’s horizon length is a function of past recommendations. Results: We prove that no algorithm can keep all customers engaged. Unfortunately, classical bandit algorithms provably overexplore, causing every customer to eventually disengage. Motivated by the structural properties of the optimal policy in a scalar instance of our problem, we propose modifying bandit learning strategies by constraining the action space up front using an integer program. We prove that this simple modification allows our algorithm to perform well by keeping a significant fraction of customers engaged. Managerial implications: Platforms should be careful to avoid overexploration when learning customer preferences if customers have a high propensity for disengagement. Numerical experiments on movie recommendations data demonstrate that our algorithm can significantly improve customer engagement.

Green Supplier Selection Based on Customer Needs Using Markov Chain and MCDM Method

Supplier selection is a problem that has been widely discussed and addressed from different angles, but few works address the supplier selection problem by considering the needs of customers. After a literature review of the studies done on this topic none of them considered the changing desires and behavior of customers when evaluating green suppliers. This contribution then, will aim to design a green supplier selection model based on customer need using a recent MCDM decision making method and the Markov chain. The Markov chain is used to model and track changes in customer preferences and find a transition model. Then the (BWM) method is used to select the best ecological supplier.

Phrase Embedding and Clustering for Sub-Feature Extraction from Online Data

Recently, online user-generated data has been used as an efficient resource for customer analysis. In the product design area, various methods for analyzing customer preference for product features have been suggested. However, most of them focused on feature categories rather than product components which are crucial in practical applications. To address that limitation, this paper proposes a new methodology for extracting part-level features from online data. First, the method detects phrases in the data and filtered them using product manual documents. The filtered phrases are embedded into vectors, and then they are divided into several groups by two clustering methods. The resulting clusters are labeled by analyzing items in each cluster. Finally, cue phrases for sub-features are obtained by selecting clusters with labels representing product features. The proposed methodology was tested on smartphone review data. The result provides feature clusters containing sub-feature phrases with high accuracy. The obtained cue phrases will be used in analyzing customer preferences for part-level features and this can help product designers determine the optimal component configuration in embodiment design.

Sustainability as a factor of changing marketing strategies based on the customers´ preferences in context of different generations in Slovakia

The most up-to-date challenge of modern marketing is the need to incorporate sustainability principles into marketing strategies. Promoting the principles of sustainability requires setting environmental objectives at the enterprise level and devising marketing strategies that meet the environmental requirements and customer preferences. The article deals with two basic topics, the issue of environmental marketing against the background of customer preferences and generations of consumers, more precisely as they were profiled in Slovakia. Examining the preferences of customers of different generations aimed to prove that implementing environmental marketing principles is necessary. Although the aim of the research was to correlate selected findings with the preferences of the environmental objectives of different generations, the research that focused on the behavior of different generations of consumers under the sustainability concept revealed some original findings concerning the assessment of ethnocentrism under the sustainability concept.