Desktop version

Home arrow Business & Finance

  • Increase font
  • Decrease font

<<   CONTENTS   >>

Features of Supply Chain Analytics

With advances in supply chain analytics, several organisations can safeguard their business reputation and ensure long-term sustainability [15].

• Collaborative: A cloud-based network is used to collaborate with all the entities of the supply chain allowing collaboration and involvement of several organisations.

  • Connected: Ability to make use of all sorts of information and data - structured and organised, unstructured, and traditional data.
  • Cyber aware: Connectivity and collaborative features make it highly essential for the supply chain to be particularly aware of intrusions from cyber and cyber hacks.
  • Cognitively enabled: Supply chain is automated and self-learning. The AI platform renders itself to be the foreground for the future by gathering and collecting, coordinating, and organising, and managing actions and decisions all through the chain [16].
  • Comprehensive: Insights are required to be spontaneous and comprehensive. Delay and latency are undesirable in the future of the supply chain.

Opportunities and Applications for Supply Chain Analytics

This section illustrates the different opportunities and applications for supply chain analytics in big data.

Opportunities for Supply Chain Analytics

With analytics, Supply Chain performs with high targets to enhance in several aspects, including user requirement prediction, Supply Chain assessment, the overall efficiency of Supply Chain, time taken to react, risk assessment.

  • • Enhancing predictions of user requirement: Understanding customer and user requirements plays a very vital role. Meeting the user’s requirements with the precise product and to the precise user at the precise time and place is key to earning and perpetuating customer satisfaction and loyalty.
  • • Enhancing efficiency: Incorporating analytics to approximately calculate and make decisions that are cost-efficient enhances the efficiency all-round the supply chain [18]. Reduction of cost and spend analytics has persistently been the top priority in Supply Chain.
  • • Refining Assessment of Risk in the Supply Chain: Better prediction and assessment of risk and its possible impact by evaluating an enormous amount of historical data and risk mapping techniques using predictive analysis to reduce the impact are highly essential.
  • • Upgrading traceability: For improved tracking of products from production to retail, enhancing traceability is essential. Upgraded tracking abilities provide much better control over several supply chain processes. The primary purpose is to guarantee a better flow' of products.

Process Specific applications of Big Data Analytics

The steps involved in the flow' of the supply chain for a process-specific application are illustrated in Figure 2.2 and Table 2.1. Supply Chain is considered to be a web of

Process of supply chain for process specific application

FIGURE 2.2 Process of supply chain for process specific application.


Summary of Process Specific Applications

SI No.





  • Risk evaluation and resilience planning
  • Minimise the risk of investments on groundwork and external agreements and contracts
  • Constant supervising of performance



• Reduce storage capacity and distribution



  • Market intelligence for all-sized enterprises Information on parameters of production, such as the forces that are required in assembly operations or differences of dimensions between parts, can be recorded and analysed
  • support the analysis of root-cause of future defects



  • Optimal routing
  • Real-time optimisation of routes
  • environmental domain intelligence and awareness
  • verification of addresses
  • pick-up and delivery spots
  • Improve Supply Chain Traceability
  • Deliver)' Routes Real-time optimisation

numerous trades and associations [19]. It unfolds the diverse tasks implicated with fabricating a product and services beginning from the idea stage till distribution to the users.

i. Plan

• Major data-driven operation in the supply chain is planned.

  • • There is a significant possibility to reformulate the procedure of planning, with the use of fresh data from sources including the internal origin and extrinsic origin to derive real-time requirement and delivery model. Several organisations make use of the latest information sources to upgrade planning and their demand understanding abilities [20].
  • • With clarity and visibility on all sorts of data, the magnitude for production is possible to be evaluated instantaneously with the intention to recognise inconsistency between requirement and delivery [21]. This makes it possible to initiate activities, such as changes in rates, promotion timings or to make necessary realignments.
  • • For example, several online enterprises utilise analytics, data, and forecasting to modify recommendations of products to users. There is an increase in requirement with such compellingness towards products that are available in stock.

ii. Source

  • • Based on the transactional ground, several processes associated with the supply chain can be recognised and identified in real-time to mark any variations from the routine fashion of delivery [22].
  • • Data Analytics is also known to drive strategic decisions. Organisations are also discovering risk management possibilities through predictive analytics by means of mapping their supply chains and using worldwide information and data from social networks about fire mishaps, strikes, or bankruptcies, the organisation can supervise supply disruptions and take necessary decisions before their competitors.

iii. Manufacturing

  • • Manufacturing can be improved by Big Data Analytics manufacturing.
  • • Information on parameters of manufacturing, such as the forces that are required in assembly operations or differences of dimensions between parts, can be recorded and analysed to hold up the analysis of reasons of blemishes, although it has the slightest possibility of its occurrence in the future.

iv. Warehousing

  • • Logistics has been very economic. Organisations have always invested in techniques and technologies that create a competitive advantage.
  • • There are many improvements and advances seen in warehousing.
  • • New innovative technologies, data and information sources, predictive and modern analytical methods are constituting novel opportunities in warehouses [23].
  • • Examples
  • - Chaotic Storage mechanism that capacitates the effectual warehouse space utilisation and reduces the distance for travel for personnel.
  • - Warehouses of High-rack bay have the ability to automatically rearrange pallets overnight to rearrange schedules for the next day optimally.

v. Transportation

  • • Several Organisations are already making use of analytics to enhance their operations. For example, truck companies are making use of analytics on their fuel consumption to intensify their driving efficiency and GPS techniques to minimise waiting periods by taking into consideration assigning warehouse inlets on time.
  • • Several Delivery Organisations are making use of real-time routing for deliveries to end-users in dependence on the traffic information and truck’s location on the road [24].

vi. Point of Sale

  • • Data and information-driven optimisation can always provide a competitive advantage.
  • • Advanced analytics can assist organisations in making judgements regarding the products to be placed in positions that are in high value, like the end of the aisle, and duration of their retention in that location.

It can also enable them with the opportunity to explore the benefits of sales attained by congregating interconnected products together.

• Retailers are monitoring a challenging activity on sales [25] for the detection and prevention of out-of-stock by using indicators to indicate when the products are out-of-stock. If a product that is purchased every few minutes does not appear at the tills, a notification is triggered to have someone check if the product on the shelf is out-of-stock. More such creative and innovative technologies are being processed; one such includes the fitting of sensors that are light-weighted on shelves as well as using in-store cameras in order to monitor and detect levels of stock on the shelves.

Tools for Supply Chain Analytics

Big data tools that are accessible for the supply chain are used to explore and integrate data, perform mathematical analysis, use accurate visual techniques for presentation, and comprehend the data storage system. Table 2.2 lists down some of such tools. In order to develop a system for making decisions, the summarisation of all the tools is a vital task in Supply Chain Analytics [26].

Supply Chain Analytics Methods

The Methodology can be categorised into descriptive, predictive, and perspective analytics [28,29].

Interpretation of the past data for better perception and comprehension of the changes occurring in any organisation are descriptive analytics. It is a scope of statistics that determines on collecting and condensing of information for better interpretation [30]. Predictive Analytics, at its elemental ground, pursues to identify and discover patterns and represents the interconnection between data. To make predictions, numerous different statistical techniques such as machine learning, data mining, predictive modelling are incorporated to analyse the present and past data [31]. Prescriptive Analytics goes well past predictive analytics by describing the activity


Tools for Supply Chain Analytics



R programming

An open-source, free tool used for statistical analysis. Built on command-line interfaces. For processing and performing analysis, and developing statistical software, this tool is used by data miners and statisticians.


It is a tool for optimisation. It is used to optimise linear, non-linear, integer programming problems. The tool can be used as an assistance for documentation. It is known for modelling expressions easily.


This tool is associated with both structured and unstructured data. It performs analysis and generates reports for the two types of data. It provides accurate visualisation techniques, easy access to information. Also performs exploring and integration of data.


A database program that is used for documentation. It is categorised as a NoSQL database program. It provides assistance in warehouse and storage, numbering and indexing, aggregating and collecting data.

Drop Shipping Management Tool (DSM)

This tool controls and handles the maintenance and support for customers on the foundation of past sales, reports, and issues faced. The DSM tool is one of the best tools in the category' of drop shipping arbitrage.


This tool is associated with extracting data from a diverse group of data and information sources, apprehends, and condenses the information gathered for precise presentation in a standard format with the intention of easy processing.

Map Reduce

It centralises on tasks scheduling and monitoring. And, it performs re-execution of the tasks in the situation of a failure. The map-reduce methodology is used to operate on the humongous quantity of data. The technique is divided into two activities: mapping and reducing. Input data are split into several individualistic blocks that are processed by the mapping technique. And, the entire input data are divided and sorted to reduce the amount of work [27].

Making decisions and taking actions with the help of descriptive, predictive, and perspective analytics

FIGURE 2.3 Making decisions and taking actions with the help of descriptive, predictive, and perspective analytics.

plan required to reach the anticipated results and understand the interconnected consequence of every decision.

The relationship between the three models of analytics is illustrated in Figure 2.3 [32]. Big data analysed using the descriptive and predictive model of analysis is further proceeded with the perspective model of analysis, and the acquired and gathered information is used to make decisions.

<<   CONTENTS   >>

Related topics