Smart Buyer: A Bayesian Network modelling approach for measuring and improving procurement performance in organisations
Section snippets
Introduction and motivation
Procurement as the enabler of acquiring goods and services is undoubtedly an inevitable part of any business. It is also an increasingly complex activity in relation to the features that it provides, thereby requiring the cooperation of different disciplines and departments to achieve its final goal successfully. The effective management of the supply chain in any organisation is the key to achieving a competitive advantage and procurement is one of the critical activities in building and
Literature review
In this section, we present our survey of the literature from three perspectives. The first perspective discusses those approaches that focus on improving different activities that come under procurement. The second perspective discusses those approaches that aim to evaluate performance in general, and the third perspective is related to the work that deals with procurement performance evaluation.
Preliminaries
Before we explain the Smart Buyer framework for procurement measurement and management, we explain the important preliminary concepts as follows.
Smart Buyer: Previously, we highlighted the need for organisations to measure and manage their procurement performance by considering all the KPIs. Accordingly, a Smart Buyer is defined as a buyer or organisation which first measures its procurement performance by considering all the KPIs and then uses this for managing and improving its practices.
Smart Buyer framework for achieving procurement excellence
The Smart Buyer framework for achieving Procurement Excellence as shown in Fig. 2 comprises three stages. Stage 1 deals with performance measurement whereas stages 2 and 3 deal with performance management. Stage 1 enables organisations to know, understand, quantify and rank their current procurement level. Stage 2 assists organisations to determine if their current procurement level is the best they can achieve according to their limitations and stage 3, depending on the procurement standing
Bayesian Network construction
To build a BN, firstly create a causal graphical model using a directed acyclic graph that will represent interdependencies among the different KPIs. The associated probabilities with BNs’ nodes are belief degree that can be assigned by the knowledge engineer who uses BNs for modelling. There are two ways of constructing BNs. One way is to use structure learning algorithms [18], [29], [30]. Since these algorithms require a great amount of data, it is a common practice to use the second method
Using a BN model to achieve procurement excellence
In the first part of this section, we build our BN model based on the proposed algorithms in Section 5. In the second part, we demonstrate different types of reasoning which can be utilised for procurement performance measurement and procurement management, thereby leading to procurement excellence.
Application showing the applicability of the smart buyer framework to measure and improve an organisation's procurement performance
In June 2017, USA TODAY reported that in the previous decade, the Pentagon wasted $28 million on supplying free camouflage uniforms to the Afghan military troops [93] which were the wrong colour. Unfortunately a “forest” pattern was chosen for these uniforms while only 2.1% of Afghanistan is covered by forest, making troops extremely vulnerable to attack. The Afghan troops avoided using the uniforms, resulting in the waste of the money spent on them. Let us consider this a procurement
Conclusion and future work
In this article, we reviewed existing literature on how an organisation can achieve procurement excellence. We divided our review into three categories, one that focused on improving activities that come under procurement and the other two that focused on performance evaluation in general and procurement performance evaluation in particular. As we reported, while there are many approaches in the existing literature aiming to improve procurement practices, very few efforts consider all these
References (104)
- et al.
An integrated approach for supplier portfolio selection: lean or agile?
Expert Syst. Appl.
(2015) - et al.
An analysis of metrics used to measure performance in green and sustainable supply chains
J. Cleaner Prod.
(2015) - et al.
Supplier selection and order lot sizing modelling: a review
Comput. Oper. Res.
(2007) - et al.
Supplier management in developing countries
J. Cleaner Prod.
(2013) - et al.
Causal modelling alternatives in operations research: overview and application
Eur. J. Oper. Res.
(2004) - et al.
Green supplier development program selection using NGT and VIKOR under fuzzy environment
Comput. Ind. Eng.
(2016) - et al.
Reviewing and improving performance measurement systems: an action research
Int. J. Prod. Econ.
(2011) - et al.
AHP-based approaches for supplier evaluation: problems and perspectives
J. Purch. Supply Manage.
(2012) - et al.
Strategically managed buyer – supplier relationships and performance outcomes
J. Oper. Manage.
(1999) - et al.
A review of methods supporting supplier selection
Eur. J. Purch. Supply Manage.
(2001)
Effect of purchase volume flexibility and purchase mix flexibility on e-procurement performance: an analysis of two perspectives
J. Oper. Manage.
Evaluating green supplier development programs with a grey-analytical network process-based methodology
Eur. J. Oper. Res.
Purchasing performance evaluation: with data envelopment analysis
Eur. J. Purch. Supply Manage.
A review of performance measurement: towards performance management
Comput. Ind.
Bayesian network analysis of safety culture and organisational culture in a nuclear power plant
Saf. Sci.
Using Bayesian networks to analyze occupational stress caused by work demands : preventing stress through social support
Accid. Anal. Prev.
Critical factors for sub-supplier management: a sustainable food supply chains perspective
Int. J. Prod. Econ.
Top and bottom line relevance of purchasing and supply management
J. Purch. Supply Manage.
Exploring e-procurement value for construction companies in Malaysia
Procedia Technol.
Multi-criteria decision making approaches for supplier evaluation and selection: a literature review
Eur. J. Oper. Res.
A Bayesian Network approach to the evaluation of building design and its consequences for employee performance and operational costs
Build. Environ.
Bayesian-network-based safety risk assessment for steel construction projects
Accid. Anal. Prev.
Designing a performance measurement system: a case study
Eur. J. Oper. Res.
Assessing supplier environmental performance: applying analytical hierarchical process in the United Arab Emirates healthcare chain
Renewable Sustainable Energy Rev.
Investigating the impact of procurement alignment on supply chain management performance
Procedia Technol.
Constructing a Bayesian network model for improving safety behavior of employees at workplaces
Appl. Ergon.
State of the art literature review on performance measurement
Comput. Ind. Eng.
Achieving purchasing competence through purchasing performance measurement system design-a multiple-case study analysis
J. Purch. Supply Manage.
Performance evaluation of purchasing and supply management using value chain DEA approach
Eur. J. Oper. Res.
Supply-management maturity, cost savings and purchasing absorptive capacity: testing the procurement–performance link
J. Purch. Supply Manage.
Identifying Robust portfolios of suppliers: a sustainability selection and development perspective
J. Cleaner Prod.
Purchasing models and organisational performance: a study of key strategic tools
J. Bus. Res.
Predicting purchasing performance: the role of supplier development programs
J. Mater. Process. Technol.
Revisiting the make-or-buy decision: conveying information by outsourcing to rivals
Acc. Rev.
Evaluating ecological sustainable performance measures for supply chain management
Supply Chain Manage.
Toward a more agile government: the case for rebooting federal IT procurement
Public Contract Law J.
Measuring supply chain performance
Int. J. Oper. Prod. Manage.
Sustainable procurement in the public sector: an international comparative study
Int. J. Oper. Prod. Manage.
Purchasing performance management systems: an empirical investigation
Prod. Plann. Control
Purchasing performance: what makes the magic?
J. Purch. Mater. Manage.
Analysing organic food buyers perceptions with Bayesian networks: a case study in Turkey
Strategic supplier performance evaluation: a case-based action research of a UK manufacturing organisation
Int. J. Prod. Econ.
Innovation and public procurement–review of issues at stake
Strategic purchasing: a history and review of the literature
Int. J. Purch. Mater. Manage.
Impact of supplier management strategies on the organisational performance of ISO 9001 certified organisations
Qual. Innovation Prosperity
A review on supply chain performance measures and metrics: 2000–2011
Int. J. Prod. Perform. Manage.
Investigation into barriers to adoption of e-procurement and measures of performance
Int. J. Procurement Manage.
Supplier selection decisions in systems/software purchases
Int. J. Purch. Mater. Manage.
Cited by (24)
Artificial intelligence and machine learning in purchasing and supply management: A mixed-methods review of the state-of-the-art in literature and practice
2024, Journal of Purchasing and Supply ManagementA new scoring system for the Rapid Entire Body Assessment (REBA) based on fuzzy sets and Bayesian networks
2020, International Journal of Industrial ErgonomicsCitation Excerpt :In this step, several postures were analyzed using both REBA and FBnREBA, and the differences were investigated. One of the main characteristics of a BN is its ability to perform various types of reasoning, such as predictive, diagnostic, inter-causal, and combined reasoning (Abolbashari et al., 2018). The most effective way to reduce the risk of WMSDs can be determined using predictive reasoning.
Object semantics sentiment correlation analysis enhanced image sentiment classification
2020, Knowledge-Based SystemsCitation Excerpt :Bayesian Network is a graphical network model used to describe uncertainty causality between variables, which can deal with problems involving reasoning, diagnosis, decision risk, and reliability analysis [35–37]. Due to intuitiveness and naturalness when solved uncertainty problems, Bayesian network combining probability theory and graph theory has become one of the research hotspots of intelligent data processing recently, and is widely applied to expert systems [38], decision support [39], pattern recognition [40], machine learning [41,42] and data mining [43]. Considering the superiority of Bayesian networks, we also employ it to construct OSSCM for analyzing the relationship between object semantics and emotions in this paper.
Hybrid teaching–learning-based optimization and neural network algorithm for engineering design optimization problems
2020, Knowledge-Based SystemsCitation Excerpt :The two algorithms have their own characteristics, which can be described as follows. As the basis of artificial intelligence, neural network technique has been growing very fast in recent years, which has been used to solve many practical problems [15–27]. Interestingly, Sadollah et al. [28] proposed a novel meta-heuristic method called neural network algorithm (NNA) in 2018, which shows neural network technique can be used to design optimization algorithm.
The updating strategy for the safe control Bayesian network model under the abnormity in the thickening process of gold hydrometallurgy
2019, NeurocomputingCitation Excerpt :BN is also known as belief nets, probabilistic dependence graphs, etc., which is an important method to represent and reason for the uncertain knowledge. It has been applied in a variety of fields [20–29]. BN is represented by the directed acyclic graph.
Application of interpretable machine learning models for the intelligent decision
2019, NeurocomputingCitation Excerpt :When making economics and business management decisions, the support of machine learning methods is very useful since these methods can provide an objective, comprehensive and accurate result from database. Without these methods, emerged decisions are made by experts who may be very subjective sometimes [13,14]. Knowledge-based system used in management generates information, thus, decisions are made more objectively and effectively within groups [15–17].