Materials Today: Proceedings xxx (xxxx) xxx

Contents lists available at ScienceDirect

Materials Today: Proceedings

journal homepage: www.elsevier.com/locate/matpr

Machine learning: Best way to sustain the supply chain in the era of
industry 4.0
Devashish Nagar a, Sudhanshu Raghav a, Aman Bhardwaj a, Rajender Kumar a, Punj Lata Singh b,
Rahul Sindhwani c,⇑
a
Department of Mechanical Engineering, FET, MRIIRS, India
b
Civil Engineering Department, ASET, Amity University Uttar Pradesh, India
c
Department of Mechanical Engineering, ASET, Amity University Uttar Pradesh, India

a r t i c l e i n f o a b s t r a c t

Article history: With the rapidly growing importance in the industries on the adaptation of advanced technologies, the
Received 21 October 2020 involvement of IT-enabled systems has increased in developing the pathway for the future industry.
Received in revised form 21 October 2020 The learning’s from these technologies becomes paramount for the present industries which gives a sense
Accepted 21 December 2020
of belongingness and significance of the industry towards the market. The digital revolution world-wide
Available online xxxx
affected the physical happenings of the events in the manufacturing industries such as the procurement,
manufacturing/assembling & distribution of goods. This digital reformation is known as Industry 4.0
Keywords:
which generally means the advancement in the existing business models where all the business opera-
Machine Learning (ML)
Supply Chain (SC)
tions are interconnected with each other by digital mode (virtual representation based on operations). In
Industry 4.0 this kind of environment, it is being necessary to map all the operations digitally in such a manner so that
Resources utilization the physical flows of resources/goods will not suffer at any stage. Machine learning in the present sce-
Digital transformation nario is one of the thrust areas for the researchers and the practitioners. The output in the machine learn-
ing process is having many dependencies on the input data such as the functions and characteristics
imparted to the machine at the earlier stage. The present paper aptly reflects the thoughts and reflections
of present-day industries and the opportunities to express feelings, thoughts, and contribute towards the
future industries.
Ó 2021 Elsevier Ltd. All rights reserved.
Selection and peer-review under responsibility of the scientific committee of the 3rd International Con-
ference on Computational and Experimental Methods in Mechanical Engineering.

1. Introduction 2. Understanding the customer on an individual basis (to cre-

ate the pull from the customer end)
In industries, Supply Chain plays an extreme role in the success 3. Help in increasing the competitiveness and flexibility by
[26]. It’s a complex integration of various business entities having a addressing all the issues
variety of technology and resource utilization [51]. Though the effi- 4. Providing the dynamicity to industry to find out the solution
ciency of a supply chain is dependent on various parameters, it based on attributes such as quality, cost, time, risks, robust-
seems to be difficult to design/develop a common platform where ness, etc.
the integration of all the entities can be done centrally to enable 5. Increasing the real-time visibility of the industry environ-
industry the too quick respond to the market needs [7,21,56]. ment to take prompt decisions
Generally, the SC helps industries in the following: 6. Optimizing the resource utilization
7. Providing opportunities to organizations on various fronts
1. Establishing the strategic vision & mission of an organization such as innovation, new product development, business
strategies (B2N or B2C).
8. Developing an integrated model for scheduling problems
⇑ Corresponding author. based on location-routing in various situations such as
E-mail addresses: plsingh@amity.edu (P. Lata Singh), rsindhwani@amity.edu (R. cross-docking, direct shipment, etc.
Sindhwani).

https://doi.org/10.1016/j.matpr.2021.01.267
2214-7853/Ó 2021 Elsevier Ltd. All rights reserved.
Selection and peer-review under responsibility of the scientific committee of the 3rd International Conference on Computational and Experimental Methods in Mechanical
Engineering.

Please cite this article as: D. Nagar, S. Raghav, A. Bhardwaj et al., Machine learning: Best way to sustain the supply chain in the era of industry 4.0, Materials
Today: Proceedings, https://doi.org/10.1016/j.matpr.2021.01.267
D. Nagar, S. Raghav, A. Bhardwaj et al. Materials Today: Proceedings xxx (xxxx) xxx

9. Motivating the employees and keeping them in the produc- systems to respond to the production demand by eliminating the
tive mode as per the workflow analysis. in process delays [30]. Another CPS system involvement in the
10. Improving the performance on continuous basis and lead industries was the Augmented Operator in which the operator
towards the perfection. [10,31,32,33,35,38,44,47,48,52,53, skills are used to implement the automation which further makes
59,70,86]. an industry more flexible and adaptable [4]. In such kinds of indus-
tries, the operator has to play a variety of roles such as specifica-
The literature on manufacturing industry performance reveals
tion, monitoring, and validation of different production strategies
industrial growth dependency on the physical flow of the
[69]. Industry 4.0 has to target future aspects in industries related
resources/goods throughout the supply chain [71]. In the small-
to innovation, flexibility, and complexity [88]. The six design prin-
scale industries (having less variety in goods i.e. product-mix), it
ciples in the Industry 4.0 are the: (a) Interoperability; (b) Virtual-
is easier to manage the supply chain rather than in the large scale
ization; (c) Decentralization; (d) Real-time capability; (e) Service
(offering variety in goods). Further, the prediction on the future
orientation and; and (f) Modularity [76]. It helps in enabling the
forecast and the reliability of the forecast becomes an issue while
flexibility aspect within the organization’s operational activities
handling the supply chain in uncertain environment conditions
which results in modifying the production system into mass cus-
[72]. Now, it becomes essential to have better control over this
tomization and also helps in improving quality and productivity
value chain in the long term perspective [73].
[87,84]. Most of the industries were working on a decentralized
The automation of the industrial entities is growing rapidly and
controlling system or in some cases the autonomous models were
increasing the competition rivalries where survival in long term
used for controlling the operations in the industries [80]. These
becomes an issue for the industries [58]. For this, the industries
kinds of models are now the biggest challenge for all kinds of
are using software-enabled systems as the medium of communica-
industries because of the globalization of markets and competition
tion to enable the organizations to withstand the latest trends [9].
[12,23]. To find out the solution, Industry 4.0 is the best option
Machine learning is the tool that helps in reducing/eliminating the
which aims to boost the communication among the industrial
negative influence of the data interpretation as this has no human
stake-holders and the resources to control centrally the discrete
involvement directly. It generally incorporates the large data set as
functions of an organization [36,45]. The resources in Industry
the input in the system and responds quickly to the current requi-
4.0 are converted into intelligent objects with the aid of technology
sitions/demands of the industries [74]. It helps in recognizing the
so that they can sense and respond according to the desired situa-
situations and integrated these situations with the functions
tion for better business and societal outcomes [46,49]. The tech-
already in the system for preparing the models for analysis pur-
nologies that are playing the key roles in Industry 4.0 are the
poses. These models are further used for the decision-making pro-
Internet of Thing, Cloud Computing (CC), Big Data Analytics
cess in the industries [5]. Besides, ML is used to estimate an
(BDA), and Machine Learning and Artificial Intelligence (AI), etc.
appropriate forecast [6,63]. The present paper reveals the impor-
[14,15,37,43]. These advanced tools enable the industries to
tance of Machine Learning in the industrial supply chain and briefs
rethink resource utilization and establish a healthier relationship
on benefits to the supply chain.
among the management and the value chain across the product
lifecycle [29,83].
2. Literature review The supply chain of the industry, in general, is the path from
which the resources flow from one position to another to meet
The environment in the present scenario is dynamic and causes the customer demand. In the supply chain the statistical data
fierce competition among the manufacturing industries [17,66,77]. regarding the product/service is dependent on the various aspects
Also, in the earlier generations 1.0; 2.0, and 3.0, there were several like cost, region, gender, age, lifestyle, occupation, etc. [24,25].
issues with the industries like productivity, demand, and delivery, Machine learning is one of the best tools in today’s perspective
etc. The revolution in the IT sector started later in 1970, the move- as it is focused on the optimization of all the resource utilization
ment worldwide in the industrial sector enforced the industry to throughout the value chain [16,82]. The algorithm designed in
think on the improvement aspect i.e. both the industry efficiency machine learning to predict/sense the inputs are consumer-
and efficacy perspective [11,41,67]. The terminology of Industry centric and they allow machines to take prompt actions for the
4.0 is now studied by all the researchers and practitioners from decisions regarding the situations [42,77]. The data input can be
the developing nation [54]. The other terms for Industry 4.0 are done by all the three modes of learnings i.e. with the help of a spe-
used such as smart manufacturing; intelligent manufacturing and cially designed questionnaire or by constant monitoring (feedback
factories of the future, etc. Industry 4.0 was firstly introduced in based) etc. [22]. Machine learning generally provides reliable infor-
Germany in 2011, persistence to the customer needs and consis- mation as it precisely predicts the situation and helps in finding
tency in delivering the goods [87,4,50]. It enables and reinforces the best possible solution out of the alternative course of actions
the industrial system to respond to the trend by using several developed in the analysis [13,64,68]. In the logistic planning, ML
tools/technologies [28,55]. serves as the statistical tool to conduct an in-depth analysis of crit-
The involvement of the cyber-physical system (CPS) was ically important inputs by the market i.e. consumer feedback, mar-
noticed as the industry moves towards the future [39,61,80]. ket scenario, competitor analysis, etc. which further reduce the
Firstly, the concept of smart product was introduced which is in chances of pitfalls in potential consumers [75,81].
general the paradigm shift in the role of the workpiece from the
passive to the active one. Sufficient data is created regarding the
products like material requisition, operations in no’s and timing 3. Research gap
at different workstations, etc., and stored for further use. As and
when the demand is raised for the product by the customer, these Supply chain management generally discovers the various pos-
details and requisitions come in the role for placing the order for sibilities for the industry to optimum utilization of resources [10].
resources and coordinates with the production facilities The product demand and supply is managed by the supply chain.
[18,57,62]. Later to this, the concept of smart machines has come Still, there are so many obstacles present within the supply chain
into a role where the traditional machines are converted into smart that caused its performance throughout the value chain [3]. These
ones by replacing or modifications based on the production hierar- obstacles are due to several reasons such as the length of the sup-
chy. The machines were interconnected like the plug-and-play ply chain, uncertainty, effective communication, and the lack of
2
D. Nagar, S. Raghav, A. Bhardwaj et al. Materials Today: Proceedings xxx (xxxx) xxx

prediction on consumer behavior, etc. [19]. As far as the traditional data is labeled as per the user’s understanding and based on
supply chain management concern, the data input, and analysis labeled data machine will provide the information necessary for
were done manually that inhibits the effective handling of all the the decision making. In this case, the exact outcomes are provided
problems simultaneously [8,65]. The data collection becomes com- to the user based on labeled data. In an unsupervised learning pro-
plex where no production and/or sales outlets are more. Also, it is cess, the data collected is divided into clusters which are further
observed in some cases that the analysis was not sufficient which used for decision making [60]. In this case, the various courses of
leads to predict the negative influence of the integrity of industrial actions are introduced to the user for decision making. This learn-
operations [78]. That’s-why, it becomes difficult to objectifying the ing process is quite complex to understand as this process never
overall assessment of all the business entities of an organization used the labeled data [40]. Reinforcement learning is also known
especially in the case of dispersed (decentralized) production or as the reward based on the feedback given by the users. The nega-
the sales network [79]. The present paper will illustrate the neces- tive feedback by the user regarding any object/situation is read by
sity of machine learning in the supply chain and how it can be ben- the machine as the relation between the data and function. These
efitted to the originations. feedbacks actuate the internal system of the machine to recognize
the object/situation and respond accordingly.

4. Methodology
5. Research findings
In the present scenario, the industrial unit’s performance is a
major concern and the business owners are looking to find out Machine learning is a quite efficient solution while implement-
the advanced tools that would help the industry to enhance the ing it in the supply chain. It allows the industries to target the new
performance. In this regard, Industry 4.0 can be the better option goals of an optimum quality product with a low cost by the opti-
which enables the industries to cope with the challenges within mum utilization of resources. While implementing Machine learn-
and outside the organizational boundaries regarding the efficiency ing in the supply chain, it becomes necessary to have perfection in
and efficacy of the industries [85]. The Industry 4.0 tool, machine developing the algorithms for sensing the data inputs and the ana-
learning helps an industry to conduct all the activities automati- lyzing tools. Further, in machine learning, the rigor’s data sets are
cally such as data gathering, structuring, and analyzing which are required to interconnect with each other. This interconnection
necessary for decision making under various situations. This can should be done in such a manner that it helps in smooth the
be done by giving directions to the machines through the pre- resource functionalities. The various roles of machine learning’s
programmed certain algorithms. ML has the inbuilt features to rec- in the supply chain are shown in Fig. 2 below:
ognize the new product demand and help in designing the same
according to customer demands. In general, there are three types 5.1. Help in designing the smart workstations
of machine learning i.e. a. supervised learning; b. unsupervised
learning; and c. reinforced learnings as shown in Fig. 1 below [40]. The workstation generally refers to a place where the machines
In supervised learning, the labeled data i.e. data related to the transform the raw material into semi/fully finished goods. Here
functions/activities of any organization are entered into the smart workstations mean combining the machine characteristics
machine and integrated with the various situations. Further, the with the other machines on the shop floor having a dependency

Fig. 1. Machine learning taxonomy.

3
D. Nagar, S. Raghav, A. Bhardwaj et al. Materials Today: Proceedings xxx (xxxx) xxx

Fig. 2. ML Roles in supply Chain.

on each other and providing the instructions to all the machines in 5.4. Helps in increasing the cross-functionality among teams
such a manner so that the resource utilization can be optimized
easily. Earlier this optimization work was done under the guidance The literature on supply chain reveals that the better outcomes
of experienced personals and referee as continuous improvement. of SCM can be attained by implementing the IT-enabled system.
But now, sustainable activities are needed to be aligning to achieve But unfortunately, the industries are not integrating all the stake-
the industry objectives effectively [27,34]. holders of SCM with the IT-enabled systems. This makes things
more challenging while accomplishing shared goals especially in
dealing with the work done by a cross-functional team. Also, the
decision regarding the product mix not only employs the extensive
5.2. Help in providing the back support to the decision-making process work capacity but also uses the quite complex tools/technologies
in an organization to conduct repeated crash-tests for reducing the delays. The emer-
gence of machine learning in the supply chain will provide a com-
In the industries, the decision regarding operations such as pro- mon platform for cross-functional teams to work with greater
curement, production, distribution is having an impact on industry insights/intelligence across the teams. This will further lead to
performance. Any mistake in analyzing the environment would eliminating the unevenness in the supply chain and activities are
cause a severe loss to the industries. Machine learning has the fea- done smoothly.
ture of analytical evaluation which helps in capacity building in an
organization while taking the decisions in the industrial opera- 5.5. Helps in accelerating the operations
tions. Machine learning helps in providing decision support to
the industry i.e. ‘which kind of material is available in the market The earlier technologies successfully help in planning, organiz-
for the quality product and at what cost?’ ing, and scheduling work right from procurement, production,
stock, distribution, etc. In addition to that, the inclusion of machine
learning will help in acceleration in the performance of all the
operations within and outside the organizational boundaries
5.3. Helps in handling the scalability through prediction and recognition of data related to a particular
cause. The automated signals generated based on the prediction
The implementation of SCM helps an organization to scale up then helps in the decision making and improves the interconnec-
the business because it can deal with a large no of verticals simul- tivity among the various operations. Forex. In the case of logistic
taneously. Still, the response rate is not quick enough in the tradi- planning and execution, machine learning accelerates the logistic
tional supply chain. Planning and delivering in the sudden influx of operation by finding the optimum solution for the query like
new orders requires enough time to understand which further ‘How fast the industry can deliver the goods to the consumers with
cause delay in deliveries. These delays sometimes caused the deliv- the available alternatives in logistics?
ery of the goods. Also, in fewer cases, it causes a negative impres-
sion on the brand, especially where the competition of the product 5.6. Helps in the development of new products/services
in the niche are at of extreme level. This greatly concerns the heavy
equipment industry where the shortest downtimes can lead to In industrial psychology, it is not an easy task to develop and
colossal financial losses. ML-based software development allows launch new products/services in the market. It requires the proper
for minimizing these risks. For a sustainable supply chain, machine plan and schedule for development and launch. There is in-depth
learning can play a tremendous role because it helps in dealing preliminary research on the market regarding targeted audiences
with uncertainty and keeps the industry ready for the upcoming and the product/service that they need? An industry utilizes its
challenges. lot of resources to conduct this kind of researches to achieve the
4
D. Nagar, S. Raghav, A. Bhardwaj et al. Materials Today: Proceedings xxx (xxxx) xxx

objectives. Yet, this research can’t direct an organization to a 5.10. Helps in deciding the price of a good/service
proper outcome in all the cases. Machine learning works with user
interface and once the data-sets are introduced to the system, the Determining pricing is the crucial task and considers both (the
system concludes all the consequences. Further helps in validating internal and external) determinants contributing to manufactur-
the consequence and maintaining transparency. ing/generating the product/service. It is important while determin-
ing the price, to position all these determinants in such a manner
5.7. Helps in effective supplier management that they should help in pricing which generally meets the cus-
tomer expectation and profitable to the manufacturer. Mostly, it
In the supply chain, supplier collaboration is one of the biggest is observed that the products fail to target the customers just
challenges to handle. Also, the supplier quality management i.e. because of inappropriate pricing determination at the manufac-
the product/services delivered by the suppliers are of acceptable turer/service provider’s end [34]. ML helps an organization to
quality or not is also another aspect. The machine learning imple- decide the price based on real-time data and if required, help in
mentation in the supply chain will lead to manage the supplier deciding the price with additional offers/promotions to increase
quality as it provides a powerful pattern recognition technique. the market share.
These patterns offer a quick response to the supplier’s quality level
with high accuracy and also create the logs for all activities that 5.11. Safeguard in harnessing the uncertainty
happened between supplier and manufacturer. Further, machine
learning precisely examines the products/materials supplied to In the industries, the presence of decentralization in the organi-
the industry and confirms the adherence to meeting the minimum zational structure limits the scope of SCM while discussing sustain-
criteria. able or consistent performance. ML is having the real-time
capability inputs about the resources and activity in respect of
5.8. Helps in improving the demand and production planning quantity and time. Based on this, ML collects the data; does analy-
sis, and provides the necessary inputs to decide to deal with the
The concept of the supply chain was originated to bridge the dealt situations. ML allows industries to reduce human interven-
gap between supply and demand in the earlier 19th century. But tion and at the same time, boost the preciseness and effectiveness
now it becomes a powerful tool to increase the industry effective- of work processes.
ness by integrating all the stakeholders and optimizing their work.
Still, while working on demand and production planning in the tra- 5.12. Helps in improving consumer satisfaction
ditional supply chain is not the effective one and that’s-why the
concept of a sustainable supply chain comes into existence. Also, In the supply chain, the customer experience is kept at the
the lack of objectiveness in the human experts bound the utmost because it is directly related to the demand for products/
researches on the data analysis on demand prediction in the tradi- services. The higher the consumer experience helps in increasing
tional supply chain. The literature on SCM reveals that the analysis demand and vice-versa. ML will help the consumers to find real-
in the traditional supply chain was influenced by the biases of the time data by enabling the features within the system. It enables
decision-maker and the unjustified market speculations. For that a quick response to the consumer query/feedback that further
purpose, the inclusion of machine learning is the best option. leads to greater consumer satisfaction.
Machine learning featuring better production planning because it
helps in identifying the consumer requisitions and their pattern
to purchase in different scenarios. The précised analytical informa- 6. Result & conclusion
tion is provided by the algorithms employed in the ML which helps
in neutralizing and rendering the data for verification purposes. As of today, the industries need to strengthen the supply chain
This will help an organization to stand steady among other for reasons such as market share, new consumers, creating the
competitors. brand, and many more. The present paper reveals the opportuni-
ties for the industries to capitalize on their resources. For this pur-
pose, machine learning is one of the best options, if implemented,
5.9. Helps in handling the inventory-related issues (creating pull
it can benefit the industries in both tangible and intangible man-
system)
ners. The paper also gives an insight into the areas where indus-
tries mostly lose their efficient resources just because of
In the industries, there are several issues related to the inven-
decentralization in the supply chain. Machine learning provides
tory like stocking cost, the product shelf-life, space requisition,
the common (centralize) platform to pursue common goals consid-
unnecessary material handling, etc. bound them to take appropri-
ering the functional capabilities of all the stake-holders. As far as
ate/prompt decisions which some time goes against the industry
the positive roles of machine learning in the supply chain there
[20]. Especially in the case of food products, the shelf-life is the big-
are few negative aspects also such as requisition of huge invest-
gest challenge because the food products if not sold in a certain
ment initially; skill-set for establishing relationships among input
period get spoiled and lost to the industry. Further, in a few cases,
data and organization functions (integration work) and the back-
the insufficiencies of the material cause the production as well as
ground history collection for all the operations and activities in
in few cases to increase the no of dispatches. Machine learning
an organization etc. In the future, the application of the SCM model
enables the industry to eliminate the buffers of inventory by keep-
in the FMCG products manufacturing industry.
ing track of the several attributes simultaneously within and out-
side the organization. This is generally known as the pull system
in which the material is procured and directly enters production CRediT authorship contribution statement
based on consumer demand. An optimum stock level further helps
in driving secure future events. With the aid of IoT systems, ML Devashish Nagar: Methodology, Writing - original draft. Sud-
helps in handling the all-around inventory issues i.e. ‘How many hanshu Raghav: Methodology, Writing - original draft. Aman
goods are in stock at the retail store/warehouses to prompt the Bhardwaj: Resources, Writing - review & editing. Rajender
decision regarding production and delivery of goods?’ Kumar: Conceptualization, Supervision. Punj Lata Singh: Investi-
5
D. Nagar, S. Raghav, A. Bhardwaj et al. Materials Today: Proceedings xxx (xxxx) xxx

gation, Project administration. Rahul Sindhwani: [30] H. Kopetz, Real-Time Systems. Real-Time Systems: Design Principles for
Distributed Embedded Applications, Boston, MA: Springer US, 2011, pp. 307-
Conceptualization.
323.
[31] R. Kumar, V. Kumar, S. Singh, Role of lean manufacturing and supply chain
characteristics in accessing the manufacturing performance, Uncertain Supply
Declaration of Competing Interest Chain Manag. 2 (4) (2014) 219–228.
[32] R. Kumar, V. Kumar, S. Singh, P. Thareja, Managing the utility of manufacturing
The authors declare that they have no known competing finan- process facilities through Lean Supply Chain, J. Adv. Res. Prod. Industrial Eng. 2
(1) (2015) 13–23.
cial interests or personal relationships that could have appeared [33] R. Kumar, V. Kumar, S. Singh, Relationship establishment between lean
to influence the work reported in this paper. manufacturing and supply chain characteristics to study the impact on
organizational performance using SEM approach, Int. J. Value Chain Manag. 7
(4) (2016) 352.
References [34] K. Kumar, V.S. Dhillon, P.L. Singh, R. Sindhwani, Modeling and analysis for
barriers in healthcare services by ISM and MICMAC analysis, In Advances in
Interdisciplinary Engineering Springer, Singapore, 2019, pp. 501–510.
[3] R. Bhagwat, M.K. Sharma, Performance measurement of supply chain
[35] D.M. Lambert, M.C. Cooper, Issues in Supply Chain Management, Industrial
management: a balanced scorecard approach, Computers Indus. Eng. J. 53 (1)
Marketing Management 29 (1) (2000) 65–83.
(2007) 43–62.
[36] H. Lasi, P. Fettke, H.-G. Kemper, T. Feld, M. Hoffmann, Industry 4.0. Business
[4] E. Borgia, The internet of things vision: key features, applications and open
Information System Engineering, 6 (4) (2014) 239-242.
issues, Computer Commun. 54 (2014) 1–31.
[37] R.Y.K. Lau, W. Zhang, W. Xu, Parallel Aspect-Oriented Sentiment Analysis for
[5] B. Bousqaoui, S. Achchab, K. Tikito, Machine learning applications in supply
Sales Forecasting with Big Data, Production and Operations Management 27
chains: An emphasis on neural network applications, in: 3rd International
(10) (2018) 1775–1794.
Conference on Cloud Computing Technologies and Applications, 2017, pp. 1–7.
[38] K.M.Y. Law, P. Helo, R. Kanchana, K. Phusavat, Managing supply chains: lessons
[6] R. Carbonneau, K. Laframboise, R. Vahidov, Application of machine learning
learned and future challenges, Industrial Management and Data Systems 109
techniques for supply chain demand forecasting, Eur. J. Operation Res. 184 (3)
(8) (2009) 1137–1152.
(2008) 1140–1154.
[39] J. Lee, B. Bagheri, H.-A. Kao, A Cyber-Physical Systems architecture for Industry
[7] P. Childerhouse, D.R. Towill, Analysis of the factors affecting real world value
4.0-based manufacturing systems, Manufacturing Letter 3 (2015) 18–23.
stream performance, Int. J. Prod. Res. 40 (15) (2002) 3499–3518.
[40] D. Lieber, M. Stolpe, B. Konrad, J. Deuse, K. Morik, Quality prediction in
[8] R.K. Cho, Y. Gerchak, Supply chain coordination with downstream operating
interlinked manufacturing processes based on supervised & unsupervised
costs: coordination and investment to improve downstream operating
machine learning. Procedia: CIRP-2013, 7 (2013) 193-198.
efficiency, Eur. J. Operational Res. 162 (3) (2005) 762–772.
[41] S. Madakam, R. Ramaswamy, S. Tripathi, Internet of Things (IoT): A Literature
[9] T.Y. Choi, Y. Hong, Unveiling the structure of supply network: case studies in
Review, J. Computer Commun. 03 (05) (2015) 164–173.
Honda, Acura, and Daimler Chrysler, J. Operations Manag. 20 (5) (2002) 469–
[42] K. Metaxiotis, K. Ergazakis, E. Samouilidis, J. Psarras, Decision support through
493.
knowledge management: The role of the artificial intelligence, Information in
[10] S. Chopra, P. Meindl, Supply Chain Management (Strategy, planning and
Managing the Computer Security 11 (5) (2003) 216–221.
operation), Pearson Education, India (2/e), 2003.
[43] H. Min, Artificial intelligence in supply chain management: Theory and
[11] R. Cui, S. Gallino, A. Moreno, D.J. Zhang, The operational value of social media
applications, Int. J. Logistic Res. Appl. 13 (1) (2010) 13–39.
information, Prod. Operations Manag. 27 (10) (2018) 1749–1769.
[44] V.K. Mittal, R. Sindhwani, V. Kalsariya, F. Salroo, K.S. Sangwan, P.L. Singh,
[12] F. De Felice, A. Petrillo, F. Zomparelli, Prospective design of smart
Adoption of integrated lean-green-agile strategies for modern manufacturing
manufacturing: an Italian pilot case study, Manuf. Lett. 15 (2018) 81–85.
systems, Procedia Cirp 61 (2017) 463–468.
[13] A. Dey, Machine learning algorithms: a review, Int. J. Computer Sci.
[45] V.K. Mittal, R. Sindhwani, P.L. Singh, V. Kalsariya, F. Salroo, Evaluating
Information Tech. 7 (3) (2016) 1174–1179.
significance of green manufacturing enablers using MOORA method for
[14] Y. Duan, J.S. Edwards, Y.K. Dwivedi, Artificial intelligence for decision making
Indian manufacturing sector. In Proceedings of the International Conference
in the era of Big Data—evolution, challenges and research agenda, Int. J.
on Modern Research in Aerospace Engineering. Springer, Singapore, 2018, pp.
Information Manag. 48 (2019) 63–71.
303-314
[15] G. Dutta, R. Kumar, R. Sindhwani, R.K. Singh, Digital transformation priorities
[46] V.K. Mittal, R. Sindhwani, H. Shekhar, P.L. Singh, Fuzzy AHP model for
of India’s discrete manufacturing SMEs–a conceptual study in perspective of
challenges to thermal power plant establishment in India, Int. J. Operational
Industry 4.0, Competitiveness Review: Int. Business J. (2020).
Res. 34 (4) (2019) 562–581.
[16] M. Fasli, Y. Kovalchuk, Learning approaches for developing successful seller
[47] M. Mokhtarinejad, A. Ahmadi, B. Karimi, S.H.A. Rahmati, A novel learning
strategies in dynamic supply chain management, Inform. Sci. (NY) 181 (16)
based approach for a new integrated location-routing and scheduling problem
(2011) 3411–3426.
within cross-docking considering direct shipment, Applied Soft Computing 34
[17] B.B. Flynn, R.G. Schroeder, E.J. Flynn, World class manufacturing: an
(2015) 274–285.
investigation of Hayes and Wheelwright’s foundation, J. Operations Manag.
[48] P.W. Murray, B. Agard, M.A. Barajas, Forecasting supply chain demand by
17 (3) (1999) 249–269.
clustering customers, IFAC: Proceeding 48 (3) (2015) 1834–1839.
[18] E. Francalanza, J. Borg, C. Constantinescu, A knowledge-based tool for
[49] T.D. Oesterreich, F. Teuteberg, Understanding the implications of digitisation
designing cyber physical production systems, Computer Industry 84 (2017)
and automation in the context of Industry 4.0: A triangulation approach and
39–58.
elements of a research agenda for the construction industry, Computers in
[19] R.M. Garfamy, Supplier selection and business process improvement: an
Industry 83 (2016) 121–139.
exploratory multiple case study, Int. J. Operational Res. 10 (2) (2011) 240–255.
[50] J. Posada, C. Toro, I. Barandiaran, D. Oyarzun, D. Stricker, R.D. Amicis, E.B. Pinto,
[20] J.L. Gattorna, D.W. Walters, Inventory Management in the Supply Chain.
P. Eisert, J. Dollner, I. Vallarino, Visual Computing as a Key Enabling
Managing the Supply Chain, (1996) 122-136.
Technology for Industrie 4.0 and Industrial Internet, Computer Graphics and
[21] A. Gunasekaran, C. Patel, E. Tirtiroglu, Performance measures and metrics in a
Applications, IEEE 35 (2) (2015) 26–40.
supply chain environment, Int. J. Operations Prod. Manag. 21 (1/2) (2001) 71–
[51] A. Reichhart, M. Holweg, What Is the Right Supplier Park for Your Supply
87.
Chain? Supply Chain Forum: Int. J., 7 (1) (2006) 4-13. 218
[22] P. Harrington, Machine learning in action, Manning Publications Co., Shelter
[52] G. Reiner, M. Trcka, Customized supply chain design: problems and
Island, New York, 2012.
alternatives for a production company in the food industry. A simulation
[23] M. Hermann, T. Pentek, B. Otto, Design Principles for Industrie 4.0 Scenarios,
based analysis, Int. J. Prod. Economics 89 (2) (2004) 217–229.
in: In the proceeding of 49th Hawaii International Conference on System
[53] K.C. Richard, G. Yigal, Supply chain coordination with downstream operating
Sciences (HICSS), 2016, pp. 3928–3937.
costs: coordination and investment to improve downstream operating
[24] P. Hines, Benchmarking Toyota’s supply chain: Japan vs U.K, Long Range
efficiency, Eur. J. Operation Res. 162 (2005) 762–772.
Planning 31 (6) (1998) 911–918.
[54] J.D. Sachs, G. Schmidt-Traub, M. Mazzucato, D. Messner, N. Nakicenovic, J.
[25] C.-C. Hsu, K.C. Tan, V.R. Kannan, G. Keong Leong, Supply chain management
Rockström, Six Transformations to Achieve the Sustainable Development
practices as a mediator of the relationship between operations capability and
Goals, National Sustainability 2 (9) (2019) 805–814.
firm performance, Int. J. Prod. Res. 47 (3) (2009) 835–855.
[55] J.A. Saucedo-Martinez, M. Pérez-Lara, J.A. Marmolejo-Saucedo, Industry 4.0
[26] M. Hugos, Essentials of Supply Chain Management, John Wiley & Sons,
framework for management and operations: a review, J. Ambient Intelligent
Hoboken, New Jersey, 2003.
Human Computer 9 (3) (2017) 789–801.
[27] S.-H. Kang, B. Kang, K. Shin, D. Kim, J. Han, A theoretical framework for strategy
[56] J. Shah, N. Singh, Benchmarking internal supply chain performance:
development to introduce sustainable supply chain management, Procedia:
development of a framework, J. Supply Chain Manag. 37 (1) (2001) 37–47.
Social Behav. Sci. 40 (2012) 631–635.
[57] R. Schmidt, M. Möhring, R.C. Härting, C. Reichstein, P. Neumaier, P. Jozinović,
[28] H. Kagermann, J. Helbig, A. Hellinger, W. Wahlster, Recommendations for
Industry 4.0-Potentials for Creating Smart Products: Empirical Research
implementing the strategic initiative INDUSTRIE 4.0: Securing the future of
Results, in: International Conference on Business Information Systems, 2015,
German manufacturing industry, final report of the Industrie 4.0 Working
pp. 16–27.
Group, Forschungsunion, 2013.
[58] J. Siderska, K.S. Jadaan, Cloud manufacturing: a service-oriented
[29] P. Kess, K.M.Y. Law, R. Kanchana, K. Phusavat, Critical factors for an effective
manufacturing paradigm. A review paper, Eng. Manag. Prod. Service 10 (1)
business value chain, Industrial Management and Data Systems 110 (1) (2010)
(2018) 22–31.
63–77.

6
D. Nagar, S. Raghav, A. Bhardwaj et al. Materials Today: Proceedings xxx (xxxx) xxx

[59] D. Simchi-Levi, P. Kaminsky, E. Simchi-Levi, Designing and Managing the [76] U. Wagner, T. AlGeddawy, H. ElMaraghy, E. Müller, Developing products for
Supply Chain: Concepts, Strategies and Case Studies, McGraw-Hill, New York, changeable learning factories, CIRP J. Manuf. Sci. Tech. 9 (2015) 146–158.
2000. [77] S. Wang, J. Wan, D. Zhang, D.i. Li, C. Zhang, Towards smart factory for Industry
[60] A. Simon, M.S. Deo, S. Venkatesan, D.R.R. Babu, An overview of machine 4.0: A self-organized multi-agent system with big data based feedback and
learning and its applications, Int. J. Electrical Sci. Eng. 1 (1) (2015) 22–24. coordination, Computer Network 101 (2016) 158–168.
[61] R. Sindhwani, V. Malhotra, Barriers evaluation for agile manufacturing system [78] H. Wenzel, D. Smit, S. Sardesai, Artificial Intelligence and Digital
with fuzzy performance importance index approach, Int. J. Agile Syst. Manag. 9 Transformation in Supply Chain Management: Innovative Approaches for
(4) (2016) 292–301. Supply Chains, Proceedings of the Hamburg Inst. 27 (2019) 413–441.
[62] R. Sindhwani, V. Malhotra, Modelling the attributes affecting design and [79] S. Weyer, M. Schmitt, M. Ohmer, D. Gorecky, Towards Industry 4.0-
implementation of agile manufacturing system, Int. J. Process Manag. Standardization as the crucial challenge for highly modular, multi-vendor
Benchmarking 6 (2) (2016) 216–234. production systems IFAC-Papers On-Line 48 (3) (2015) 579–584.
[63] R. Sindhwani, V. Malhotra, An integrated approach for implementation of agile [80] W.K. Wong, Z.X. Guo, A hybrid intelligent model for medium-term sales
manufacturing system in an Indian manufacturing industry. Benchmarking: forecasting in fashion retail supply chains using extreme learning machine and
Int. J. (2018). harmony search algorithm, Int. J. Prod. Economics 128 (2) (2010) 614–624.
[64] R. Sindhwani, P.L. Singh, R. Chopra, K. Sharma, A. Basu, D.K. Prajapati, V. [81] T. Wuest, D. Weimer, C. Irgens, K.-D. Thoben, Machine learning in
Malhotra, Agility evaluation in the rolling industry: A case study. In Advances manufacturing: advantages, challenges, and applications, Prod. Manuf. Res. 4
in Industrial and Production Engineering. Springer, Singapore, 2019, pp. 753- (1) (2016) 23–45.
770. [82] D. Zage, K. Glass, R. Colbaugh, Improving supply chain security using big data,
[65] R. Sindhwani, V.K. Mittal, P.L. Singh, A. Aggarwal, N. Gautam, Modelling and in: International Conference on Intelligence and Security Informatics, 2013,
analysis of barriers affecting the implementation of lean green agile pp. 254–259.
manufacturing system (LGAMS). Benchmarking: Int. J. (2019). [83] L. Zhang, Y. Luo, F. Tao, B.H. Li, L. Ren, X. Zhang, H. Guo, Y. Cheng, A. Hu, Y. Liu,
[66] R. Sindhwani, P.L. Singh, V. Kaushik, S. Sharma, R.K. Phanden, D.K. Prajapati, Cloud manufacturing: A new manufacturing paradigm, Enterprise Information
Ranking of Factors for Integrated Lean, Green and Agile Manufacturing for System-UK 8 (2) (2014) 167–187.
Indian Manufacturing SMEs, in: Advances in Intelligent Manufacturing, [84] K. Zhou, T. Liu, L. Zhou, Industry 4.0: Towards Future Industrial Opportunities
Springer, Singapore, 2020, pp. 203–219. and Challenges, in: International Conference on Fuzzy Systems and Knowledge
[67] R. Sindhwani, P.L. Singh, V. Kaushik, S. Sharma, R.K. Phanden, Analysis of Discovery, 2016, pp. 2147–2152.
Barriers to Lean-Green Manufacturing System (LGMS): A Multi-criteria [85] L. Zhu, Y. Ma, L. Zhang, Ensemble model for order priority in make-to-order
Decision-Making Approach, in: Advances in Intelligent Manufacturing, systems under supply chain environment, International Conference on
Springer, Singapore, 2020, pp. 181–188. Management Science & Engineering (ICMSE) (2014) 321–328.
[68] P.L. Singh, R. Sindhwani, N.K. Dua, A. Jamwal, A. Aggarwal, A. Iqbal, N. Gautam, [86] R.V. Altekar, Supply chain management: Concepts and cases, PHI Learning Pvt
in: Evaluation of common barriers to the combined lean-green-agile Ltd, 2005.
manufacturing system by two-way assessment method, Springer, Singapore, [87] F. Almada-Lobo, The Industry 4.0 revolution and the future of Manufacturing
2019, pp. 653–672. Execution Systems (MES), J. Innov. Manag. 3 (4) (2016) 16–21, https://doi.org/
[69] G. Spezzano, A. Vinci, Pattern Detection in Cyber-Physical Systems, Procedia 10.24840/2183-0606_003.004_0003.
Computer Science 52 (2015) 1016–1021. [88] D. Assante, M. Castro, I. Hamburg, S. Martin, The use of cloud computing in
[70] G. Stewart, Supply chain performance benchmarking study reveals keys to SMEs, Procedia Computer Sci. 83 (2016) 1207–1212.
supply chain excellence, Logistics Information Management 8 (2) (1995) 38–
44.
[71] P.D. Cousins Co-editors: Benn Lawson, J. Storey, C. Emberson, J. Godsell, A.
Further Reading
Harrison, Supply chain management: theory, practice and future challenges,
Int. J. Operations Prod. Manag. 26 (7) (2006) 754–774. [1] N. Du, X. Zhi, K.L. Ming, A systematic review of the research trends of machine
[72] R.E. Spekman, J. Spear, J. Kamauff, Supply chain competency: learning as a key learning in supply chain management, Int. J. Machine Learning Cybernetics
component, Supply Chain Manag.: Int. J. 7 (1) (2002) 41–55. (2020) 1–20.
[73] E. Sucky, Inventory management in supply chain: a bargaining problem, Int. J. [2] F. Tao, L. Zhang, V.C. Venktesh, Y. Luo, Y. Cheng, Cloud manufacturing: a
Prod. Economics 93–94 (2) (2005) 253–262. computing and service-oriented manufacturing model. Proceedings of the
[74] B. Tjahjono, C. Esplugues, E. Ares, G. Pelaez, What does Industry 4.0 mean to Institution of Mechanical Engineers. Part B. Journal of engineering manufacture,
supply chain? Manufacturing Engineering Society International Conference 225 (2011) 1969-1976.
(MESIC-17), 13 (2017) 1175-1182.
[75] R. Varela, B. Tjahjono, Big data analytics in supply chain management: trends
and related research. 6th International Conference on Operation Supply Chain
management, 1(1) (2014) 2013-2014.