Search results

Purchase conversion prediction aims to improve user experience and convert visitors into real buyers to drive sales of firms; however, the total conversion rate is low, especially for e-retailers. To date, little is known about how e-retailers can scientifically detect users' intents within a purchase conversion funnel during their ongoing sessions and strategically optimize real-time marketing tactics corresponding to dynamic intent states. This study mainly aims to detect a real-time state of the conversion funnel based on graph theory, which refers to a five-class classification problem in the overt real-time choice decisions (RTCDs)—click, tag-to-wishlist, add-to-cart, remove-from-cart and purchase—during an ongoing session.

The authors propose a novel graph-theoretic framework to detect different states of the conversion funnel by identifying a user's unobserved mindset revealed from their navigation process graph, namely clickstream graph. First, the raw clickstream data are identified into individual sessions based on a 30-min time-out heuristic approach. Then, the authors convert each session into a sequence of temporal item-level clickstream graphs and conduct a temporal graph feature engineering according to the basic, single-, dyadic- and triadic-node and global characteristics. Furthermore, the synthetic minority oversampling technique is adopted to address with the problem of classifying imbalanced data. Finally, the authors train and test the proposed approach with several popular artificial intelligence algorithms.

The graph-theoretic approach validates that users' latent intent states within the conversion funnel can be interpreted as time-varying natures of their online graph footprints. In particular, the experimental results indicate that the graph-theoretic feature-oriented models achieve a substantial improvement of over 27% in line with the macro-average and micro-average area under the precision-recall curve, as compared to the conventional ones. In addition, the top five informative graph features for RTCDs are found to be Transitivity, Edge, Node, Degree and Reciprocity. In view of interpretability, the basic, single-, dyadic- and triadic-node and global characteristics of clickstream graphs have their specific advantages.

The findings suggest that the temporal graph-theoretic approach can form an efficient and powerful AI-based real-time intent detecting decision-support system. Different levels of graph features have their specific interpretability on RTCDs from the perspectives of consumer behavior and psychology, which provides a theoretical basis for the design of computer information systems and the optimization of the ongoing session intervention or recommendation in e-commerce.

To the best of the authors' knowledge, this is the first study to apply clickstream graphs and real-time decision choices in conversion prediction and detection. Most studies have only meditated on a binary classification problem, while this study applies a graph-theoretic approach in a five-class classification problem. In addition, this study constructs temporal item-level graphs to represent the original structure of clickstream session data based on graph theory. The time-varying characteristics of the proposed approach enhance the performance of purchase conversion detection during an ongoing session.

The purpose of this paper is to propose the use of graph theoretic structural modeling for assessing the possible reduction in complexity of the work flow procedures in an organization due to lean initiatives. A tool to assess the impact of lean initiative on complexity of the system at an early stage of decision making is proposed.

First, the permanent function-based graph theoretic structural model has been applied to understand the complex structure of a manufacturing system under consideration. The model helps by systematically breaking it into different sub-graphs that identify all the cycles of interactions among the subsystems in the organization in a systematic manner. The physical interpretation of the existing quantitative methods linked to graph theoretic methodology, namely two types of coefficients of dissimilarity, has been used to evolve the new measures of organizational complexity. The new methods have been deployed for studying the impact of different lean initiatives on complexity reduction in a case industrial organization.

The usefulness and the application of new proposed measures of complexity have been demonstrated with the help of three cases of lean initiatives in an industrial organization. The new measures of complexity have been proposed as a credible tool for studying the lean initiatives and their implications.

The paper may lead many researchers to use the proposed tool to model different cases of lean manufacturing and pave a new direction for future research in lean manufacturing.

The paper demonstrates the application of new tools through cases and the tool may be used by practitioners of lean philosophy or total quality management to model and investigate their decisions.

The proposed measures of complexity are absolutely new addition to the tool box of graph theoretic structural modeling and have a potential to be adopted by practical decision makers to steer their organizations though such decisions before the costly interruptions in manufacturing systems are tried on ground.

The purpose of this paper is to study the impact of restructuring in the manufacturing system at the conceptual stage using graph theoretic model.

Some restructuring decisions are conceptualized which reflect the aim of the organization to gradually evolve the manufacturing system towards a leaner structure. This is achieved by way of defining simplified procedures so that lesser hindrance in terms of cycles of interactions is encountered. The restructuring decisions are represented by five restructured configurations of the manufacturing system, through gradual removal of appropriate interaction links. The graph theoretic models are developed for original configuration and each of the new restructured configurations and the resulting structural characterization information is used to compare the structure of restructured configurations with the original configuration. The value of the coefficient of dissimilarity of each of the new configurations with respect to the original configuration is obtained to have a quantitative estimate of the simplification that may be achieved by different contemplated restructuring decisions.

The present work shows that the restructuring decisions can be represented by different configurations in the form of schematic diagrams involving minor changes in the interaction structure among subsystems of the manufacturing system. The quantitative analysis using coefficient of dissimilarity for restructuring decisions indicated that there are varying levels of impact created by five comparable restructuring decisions considered in the study. The findings have a potential to guide the restructuring efforts by identifying a focus area that can produce greater impact of restructuring.

The findings are valid for a particular case manufacturing organization which does not involve itself in extensive design activity. The study is based on the assumption that the schematic diagram and graph theoretic model captured all the relevant influencing factors of the manufacturing system.

The study provides an easy to use methodology for the practical decision makers in manufacturing industry striving to improve the performance of their organization. It can provide the analysis of restructuring decisions at the conceptual stage itself without the necessity of disturbing the normal functioning of the organization. There is a scope for identifying focus areas where the restructuring may yield comparatively greater dividends.

The study of restructuring by representing it in the form of changes in interactions among subsystems of a manufacturing system and investigation of the impact of such restructuring efforts at the conceptual stage using graph theoretic model has been carried out for the first time.

One of the major challenges for developing countries is the lack of mechanisms for the evaluation of critical success factors (CSFs) of quality initiatives, which hampers the journey toward sustainability. Lean Six Sigma (LSS) has been one of the most widely used initiatives supporting quality improvement with wastes reduction and facilitating sustainability. To expedite LSS and its spread, it is important to evaluate key CSFs. Accordingly, the purpose of this paper is to provide an approach for the evaluation of LSS-CSFs for Indian small and medium enterprises (SMEs).

The paper uses a graph theoretic approach and demonstrates the evaluation of LSS-CSFs by proposing an index. The development of index is illustrated using a set of seven prioritized CSFs based on the literature review paper (Lande et al., 2016).

This study guides about the translation of CSFs in the form of an index (number) and will benefit both researchers and practitioners, who wish to study the role of key CSFs for implementation and audit requirements for sustainability.

Authors remain confined only to Indian SMEs.

LSS possesses the potential to enhance the performance of manufacturing SMEs, but its evaluation is not easy. This attempt for offering a useful evaluation scheme involving CSFs, in the areas of LSS in developing country contexts, is the first. The approach also facilitates both quality audits and benchmarking between different sets of CSFs. The approach is generalizable and can be extended in other areas.

To represent the effect of ‘human factors in total quality management (TQM) environment’ in terms of a single numerical index by considering their inheritances and interactions.

Various human factors affecting the TQM culture in an organization are identified and discussed for the sub factors affecting them. These factors are interacting with each other and their overall effect helps an organization in attaining TQM enabled needs. The paper attempts to represent the overall effect of human factors quantitatively by developing a mathematical model using graph theoretic approach. In this approach, interaction among identified human factors is represented through digraph, matrix model and a multinomial.

The extent of human aspects present in an organization, conducive to TQM culture is represented in terms of the “human index”. It provides an insight into the human factors at system and subsystem level. The developed procedure may be useful for self‐analysis and comparison among organizations.

Since, human behaviour is difficult to predict, so are the human factors. The paper considers general factors, which may vary depending on type of organization, size of organization and geographical location. There is a scope of research in factor specific organizations.

It provides a useful methodology for organizations to assess human aspects and improve upon therein. Procedure for stepwise application of methodology is given with example that may help an industry to implement it.

The paper attempts to quantify the intangibles through systematic approach and is of value to industries to improve upon their work environment.

The purpose of this paper is to assist facility designers decide when to use the graph‐theoretic (GTH) approach to develop a block layout and when to seek another alternative that requires a lesser effort. Difficulties encountered when a GTH block layout is developed from an adjacency graph could force designers to sacrifice or change some of the adjacencies of the adjacency graph in the GTH block layout. Consequently, the value of the objective function of a GTH block layout could become less than what would be expected from the GTH approach.

A computational study is performed to assess the value of the objective function of block layouts produced by the GTH approach when adjacencies of the adjacency graph are deleted or changed in the GTH block layout and two of the procedures in the literature.

The computational study reveals that the magnitude of the decline in the value of the objective function of the GTH block layout renders it comparable to values obtained by the two procedures selected from the literature.

The results of the study could motivate layout designers to resort to various approaches to develop a block layout rather than sacrifice some adjacencies of the adjacency graph in the GTH block layout, which would adversely affect its objective function value.

The purpose of this paper is to attempt to integrate manufacturing system analysis to obtain system‐wide optimized solutions and to increase the level of comprehensiveness of the manufacturing system modelling and to develop method of characterization of manufacturing systems based on its structure.

Elements constituting the manufacturing plant and the interactions between them have been identified through a literature survey and have been represented by graph‐based model. The matrix models and the variable permanent function models are developed for carrying out decomposition, characterization and the total analysis.

Structural patterns and combination sets of subsystems interacting in various ways have been recognized as capabilities of manufacturing system in different performance dimensions. The permanent function of the manufacturing system matrix has been proposed as a systematic technique for structural analysis of manufacturing system. Also, the terms of permanent multinomial characterize the manufacturing systems uniquely and are highly useful for computational storage, retrieval, communication as well as analysis of the structural information of manufacturing system.

The structure‐based characterization technique developed has the potential of aiding the ongoing research activities in the field of benchmarking, and business process reengineering. The graph theory‐based methodology will serve as a framework to develop composite performance measures building on the performance measures of the individual elements of the manufacturing system graph in various dimensions.

Through the use of proposed methodology, a manufacturing manager will be able to make better informed decisions towards organizational efforts of improving the productivity and speed. For aiding several decisions, different “what‐if” scenarios may be generated with several structural modifications.

This graph theory‐based methodology is a novel mechanism to seamlessly integrate manufacturing system giving way to system wide optimization. The paper is an attempt to address the need for comprehensive and integrated analysis of the manufacturing system.

This study has two major objectives. First, comprehensively review the literature on transparency in supply chain management. Second, based on a critical analysis of literature, identify the attributes and sub-attributes of supply chain transparency and develop a numerical measure to quantify transparency in supply chains.

A systematic literature review (SLR) was conducted using the PRISMA approach. Utilizing SCOPUS database past eighteen-year papers search resulted in 249 papers to understand major developments in the domain of supply chain transparency. Subsequently, graph theoretic approach is applied to quantify transparency in supply chain and the proposed index is evaluated for case supply chains from pharma and dairy sectors.

It can be concluded from SLR that supply chain transparency research has evolved from merely tracking and tracing of the product towards sustainable development of the whole value chain. The research identifies four major attributes and their sub-attributes that influence transparency in supply chains, which are used to develop transparency index. The proposed index for two sectors helps to understand areas that need immediate attention to improve transparency in the case supply chains.

This paper attempts to understand the development of transparency research in supply chain using the PRISMA approach for SLR. In addition, development of mathematical model to quantify supply chain transparency is a novel attempt that would help benchmark best practices in the industry. Further, transparency index would help to understand specific areas that need attention to improve transparency in supply chains.

Reliability assessment does require an effective structural modelling approach for systems, in general and manufacturing systems are no exception. This paper aims to develop it for large manufacturing systems using graph models, a systems approach.

Structural graph models for reliability at various hierarchical levels are developed by considering a CNC cam shaft grinding machine. The system reliability expression is obtained by converting the reliability graphs into equivalent matrices, which helps to evaluate and analyse system.

Using the obtained reliability expressions at various hierarchical levels of the system, it is possible not only to evaluate its reliability from structure point of view but also to identify weak structural elements from reliability point of view.

The approach can be extended to include the influence of other parameters, such as human, component and environment, etc., on the system reliability.

The approach helps to design and develop manufacturing systems from reliability consideration by assessing their possible alternatives among these.

The suggested methodology is useful for reliability evaluation of large and complex manufacturing systems.

The purpose of this paper is to propose a methodology for evaluating and comparing supply chain relationships, specifically when, small and medium scale enterprise (SME) is considered as focal company.

The paper proposes a mathematical solution based on interpretive structural modeling and graph theory matrix to determine the supply chain relationship index. The application is demonstrated for the case of Indian automotive SMEs based on the secondary data reported.

Solution determines supply chain buyer‐supplier index for upstream and downstream. Based on which coefficient of similarity and dissimilarity are determined to evaluate the net pool of buyer‐supplier relationship on focal small and medium scale automotive component manufacturing industry.

Developed approach and results will help SMEs in general and Indian automobile component manufacturing SMEs to rethink on their supply chain relationships and identify the reasons behind their present failures and establish the criteria for win‐win partnership.

The paper addresses the following issues: how buyer‐supplier relationships can be quantified and the impact measured for the present working of focal SME; how SMEs can convince upstream and down stream supply chain players to initiate improvement on some dimensions of buyer‐supplier relationships; and on what basis change in relationships (from transactional to alliance) can be made to minimize the supply chain pressure on a focal company.