Advanced Analytics in Supply Chain

The sole role of analytics is to support decision making. Through Advanced Analytics, a supply chain can leverage more insights with more accuracy. This empowers to take decisions better, faster and/or with more confidence. Specific use-cases include the following:

Create inventory visibility and visualise which products rotate at which speed through your warehouse and why (decreased sales, increased returns). Use the available data to segment your products in high- and low-rotating units and provide this as input to your warehouse manager to relocate goods and alter safety stock levels.

Derive root-causes of delivery promise failures such as vendors who deliver to late, fulfilment partners who exceed average delivery times – and identify supply-chain improvement initiatives.

Get smarter into product development by leveraging data-driven insights on your customer- and order base: what are my customers segments, how did they grow over time, how are they in one region vs. another region, what are their shared preferences, which products features do they like

Reduce lead time by understanding when which drivers impact lead-time at what impact: which parts increase the risk of production delay, which parts require a strategic inventory? With no IT investment, a solid data-mining exercise through your supply chain order-, production- and delivery data can likely already identify low hanging fruit opportunities.

Optimise inventory space and value by forecasting demand with accuracy. Do you overestimate, you will likely overproduce and stack up inventory; do you underestimate, you’ll miss sales. Through analytics we can analyse your historical sales data and assess patterns driven by seasonality, partner activity, marketing activeness, offline sales agents, weather or even country-specific GDP. Turning these patterns into inputs, we predict sales and thus prescribe needed inventory levels.

Locate geographical growth opportunities by visualising all order, delivery- and customer-locations and deriving sweet spots for new sales hubs, production sites or warehousing depots. Assess supply-chain merger potential by visualising overlapping supply-chain networks, assessing overlap and thus assessing strategic added value.

Assess failure patterns of production machines to understand which drivers are recurrently causing failure (volumes, #batch switches, temperature, speed, operator). Then translate these drivers into inputs building an early-warning-trigger tool/model to pre-empt failure (first steps of predictive maintenance).

Deep learning for smart manufacturing: Methods and applications:


Smart manufacturing refers to using advanced data analytics to complement physical science for improving system performance and decision making. With the widespread deployment of sensors and Internet of Things, there is an increasing need of handling big manufacturing data characterised by high volume, high velocity, and high variety. Deep learning provides advanced analytics tools for processing and analysing big manufacturing data.

Fig. 1

With new technologies (e.g. IoT, big data) embraced in smart manufacturing, smart facilities focus on creating manufacturing intelligence that can have a positive impact across the entire organisation. The manufacturing today is experiencing an unprecedented increase in available sensory data comprised of different formats, semantics, and structures. Sensory data was collected from different aspects across the manufacturing enterprise, including product line, manufacturing equipment, manufacturing process, labour activity, and environmental conditions. Data modelling and analysis are the essential part of smart manufacturing to handling increased high volume data, as well as supporting real-time data processing

From sensory data to manufacturing intelligence, deep learning has attracted much attention as a breakthrough of computational intelligence. By mining knowledge from aggregated data, deep learning techniques play a key role in automatically learning from data, identifying patterns, and making decisions. Different levels of data analytics can be produced including descriptive analytics, diagnostic analytics, predictive analytics, and prescriptive analytics. Descriptive analytics aims to summarise what happens by capturing the product’s conditions, environment and operational parameters. When the product performance is reduced or the equipment failure happens, diagnostic analytics examine the root cause and report the reason it happens. Predictive analytics utilises statistical models to make predictions about the possibility of future production or equipment degradation with available historical data. Prescriptive analytics goes beyond by recommending one or more courses of action. Measures can be identified to improve production outcomes or correct the problems, showing the likely outcome of each decision.

With the advanced analytics provided by deep learning, manufacturing is transformed into highly optimised smart facilities. The benefits include reducing operating costs, keeping up with changing consumer demand, improving productivity and reducing downtime, gaining better visibility and extracting more value from the operations for globally competitiveness.


Fig. 3



Applications to smart manufacturing

Computational intelligence is an essential part of smart manufacturing to enable accurate insights for better decision making. Machine learning has been widely investigated in different stages of manufacturing lifecycle covering concept, design, evaluation, production, operation, and sustainment. The applications of data mining in manufacturing engineering are reviewed in, covering different categories of production processes, operations, fault detection, maintenance, decision support, and product quality improvement. The evolution and future of manufacturing are reviewed in, emphasising the importance of data modelling and analysis in manufacturing intelligence. The application schemes of machine learning in manufacturing are identified as summarised in. Smart manufacturing also requires prognostics and health management (PHM) capabilities to meet the current and future needs for efficient and reconfigurable production.

Fig. 8




  • How does smart manufacturing help companies?
  • How will smart manufacturing evolve in the future?


NextGen Supply Chain: The emerging role for drones

drone delivery package future

Five years is a lifetime in the world of technology, but maybe you remember how Jeff Bezos turned the supply chain world upside down in December 2013.

That’s when he dropped a bombshell on 60 minutes, walked correspondent Charlie Rose and his production team “into a mystery room at the Amazon offices and revealed a secret R&D project: ‘Octocopter’ drones that will fly packages directly to your doorstep in 30 minutes.”

Faster than you can say “same day delivery,” drones were the buzz word du jour at supply chain conferences, much like RFID following the infamous Walmart mandate about a decade earlier.


Organisations are beginning to adopt drones in the first phase of supply chain management: obtaining raw materials. Drones are also used in mining, prospecting, and land surveying applications. In farming and agriculture, UAVs are used to inspect plant health, photo-log plant growth, and map crop yields. Drones are also testing soil to help optimise water content and fertiliser usage, with the intent of improving crop yields.

Drone use in manufacturing, warehousing, and distribution facilities is expected to rise in the next five years, aiding the work-in-process inventory stage of supply chain management. UAVs promise to enhance safety and security as well as promote overall efficiency. For example, drones with cameras can “walk the perimeter” of facilities, seeing areas an ordinary security camera might not reach. Inside of facilities, drones can perform safety inspections, perform maintenance and repair functions like fixing a leaky roof, or fly across a campus to retrieve a forgotten tool – all of which could potentially reduce work hours.7

In warehousing, developers at the Massachusetts Institute of Technology say UAVs are the best new way of tracking inventory anonymously. Using RFID, QR-codes, and IoT, drones can take physical inventory. Walmart Stores, for example, is currently testing drones for that purpose. Drones can move small items quickly, reducing the need for forklifts or possibly replacing the conveyor systems often used to transport boxes around distribution centers. Outside of the warehouse, drones may also be used for supply chain deliveries. For example, UAVs could ship inventory between production facilities and distribution centers, potentially expediting order fulfilment.


In terms of barriers to adoption, there’s the usual suspects in terms of privacy, safety, security and legal barriers for the industry to overcome. According to Goldman Sachs, some of the biggest obstacles to commercial adoption are regulations imposed by the FAA stating that drone flight is limited to a pilot’s line of sight, cannot fly over 400 feet, cannot operate over people or crowds, and must be flown by someone with a remote pilot certificate.

To unlock commercial demand, drones need to be able to operate beyond line of sight, above 400 feet, autonomously, as well as over populated areas. Of course, in densely populated areas, there’s many more hurdles to cross – particularly for drone package delivery, which is expected to be much further out in terms of market adoption.


  • What are the challenges in the adoption of the Drone technology?
  • What are the applications of drones in supply chain?
  • Will drones lead to a reduction in jobs?
  • Is the investment in drones worth it for businesses?



Industry 4.0


We’re in the midst of a significant transformation regarding the way we produce products thanks to the digitisation of manufacturing. This transition is so compelling that it is being called Industry 4.0 to represent the fourth revolution that has occurred in manufacturing. From the first industrial revolution (mechanisation through water and steam power) to the mass production and assembly lines using electricity in the second, the fourth industrial revolution will take what was started in the third with the adoption of computers and automation and enhance it with smart and autonomous systems fuelled by data and machine learning.


Industry 4.0 optimises the computerisation of Industry 3.0

When computers were introduced in Industry 3.0, it was disruptive thanks to the addition of an entirely new technology. Now, and into the future as Industry 4.0 unfolds, computers are connected and communicate with one another to ultimately make decisions without human involvement. A combination of cyber-physical systems, the Internet of Things and the Internet of Systems make Industry 4.0 possible and the smart factory a reality. As a result of the support of smart machines that keep getting smarter as they get access to more data, our factories will become more efficient and productive and less wasteful. Ultimately, it’s the network of these machines that are digitally connected with one another and create and share information that results in the true power of Industry 4.0.

Industry 4.0 applications today

While many organisations might still be in denial about how Industry 4.0 could impact their business or struggling to find the talent or knowledge to know how to best adopt it for their unique use cases, several others are implementing changes today and preparing for a future where smart machines improve their business. Here are just a few of the possible applications:



Identify opportunities: Since connected machines collect a tremendous volume of data that can inform maintenance, performance and other issues, as well as analyse that data to identify patterns and insights that would be impossible for a human to do in a reasonable timeframe, Industry 4.0 offers the opportunity for manufacturers to optimise their operations quickly and efficiently by knowing what needs attention. By using the data from sensors in its equipment, an African gold mine identified a problem with the oxygen levels during leaching.

Optimise logistics and supply chains: A connected supply chain can adjust and accommodate when new information is presented. If a weather delay ties up a shipment, a connected system can proactively adjust to that reality and modify manufacturing priorities.

Autonomous equipment and vehicles: There are shipping yards that are leveraging autonomous cranes and trucks to streamline operations as they accept shipping containers from the ships.

Robots: Once only possible for large enterprises with equally large budgets, robotics are now more affordable and available to organisations of every size. From picking products at a warehouse to getting them ready to ship, autonomous robots can quickly and safely support manufacturers. Robots move goods around Amazon warehouses and also reduce costs and allow better use of floor space for the online retailer.

Additive manufacturing (3D printing): This technology has improved tremendously in the last decade and has progressed from primarily being used for prototyping to actual production. Advances in the use of metal additive manufacturing have opened up a lot of possibilities for production.

Internet of Things and the cloud: A key component of Industry 4.0 is the Internet of Things that is characterised by connected devices. Not only does this help internal operations, but through the use of the cloud environment where data is stored, equipment and operations can be optimised by leveraging the insights of others using the same equipment or to allow smaller enterprises access to technology they wouldn’t be able to on their own.

While Industry 4.0 is still evolving and we might not have the complete picture until we look back 30 years from now, companies who are adopting the technologies realise Industry 4.0’s potential. These same companies are also grappling with how to upskill their current workforce to take on new work responsibilities made possible by Internet 4.0 and to recruit new employees with the right skills.


What is the potential of industry 4.0?

What are the challenges in implementation?




Artificial Intelligence in Supply Chain


The potential of AI enhancing everyday business activities and strategies hasn’t just sparked the interest of people and organisations globally, but has initiated rapid implementation.

AI was broken down into two categories:

  • “Augmentation: AI, which assists humans with their day-to-day tasks, personally or commercially without having complete control of the output. Such Artificial Intelligence is used in Virtual Assistant, Data analysis, software solutions; where they are mainly used to reduce errors due to human bias.
  • Automation: AI, which works completely autonomously in any field without the need for any human intervention. For example, robots performing key process steps in manufacturing plants” (com 2017).

Enhancing Productivity and Profits.

Understanding these two categories of AI capacities is important for future implementation of AI into business work tools. In particular, the application of AI into Supply Chain related-tasks holds high potential for boosting top-line and bottom-line value.

The graphic below shows a breakdown of the applications of AI in 835 different companies in the past year.

 How can AI be applied within SCM activities?

  1. Chatbots for Operational Procurement:

 Streamlining procurement related tasks through the automation and augmentation of Chabot capability requires access to robust and intelligent data sets, in which, the ‘procuebot’ would be able to access as a frame of reference; or it’s ‘brains’

As for daily tasks, Chatbots could be utilised to:

  • Speak to suppliers during trivial conversations.
  • Set and send actions to suppliers regarding governance and compliance materials.
  • Place purchasing requests.
  • Research and answer internal questions regarding procurement functionalities or a supplier/supplier set.
  • Receiving/filing/documentation of invoices and payments/order requests (Smith 2016).
  1. Machine Learning (ML) for Supply Chain Planning (SCP)

Supply chain planning is a crucial activity within SCM strategy. Having intelligent work tools for building concrete plans is a must in today’s business world.

ML, applied within SCP could help with forecasting within inventory, demand and supply. If applied correctly through SCM work tools, ML could revolutionise the agility and optimisation of supply chain decision-making.

By utilising ML technology, SCM professionals — responsible for SCP — would be giving best possible scenarios based upon intelligent algorithms and machine-to-machine analysis of big data sets. This kind of capability could optimise the delivery of goods while balancing supply and demand, and wouldn’t require human analysis, but rather action setting for parameters of success.

  1. Machine Learning for Warehouse Management

Taking a closer look at the domain of SCP, its success is heavily reliant on proper warehouse and inventory-based management. Regardless of demand forecasting, supply flaws (overstocking or under stocking) can be a disaster for just about any consumer-based company/retailer.

“A forecasting engine with machine learning, just keeps looking to see which combinations of algorithms and data streams have the most predictive power for the different forecasting hierarchies” ( 2017).

ML provides an endless loop of forecasting, which bears a constantly self-improving output. This kind of capabilities could reshape warehouse management as we know today.

  1. Autonomous Vehicles for Logistics and Shipping

Intelligence in logistics and shipping has become a center-stage kind of focus within supply chain management in the recent years. Faster and more accurate shipping reduces lead times and transportation expenses, adds elements of environmental friendly operations, reduces labor costs, and — most important of all — widens the gap between competitors.

If autonomous vehicles were developed to the potential — that certain business analysts and tech gurus have hypothesised — the impact on logistics optimisation would be astronomical.

“Where drivers are restricted by law from driving more than 11 hours per day without taking an 8-hour break, a driverless truck can drive nearly 24 hours per day. That means the technology would effectively double the output of the U.S. transportation network at 25 percent of the cost” ( 2016).

  1. Natural Language Processing (NLP) for Data Cleansing and Building Data Robustness

NLP is an element of AI and Machine Learning, which has staggering potential for deciphering large amounts of foreign language data in a streamlined manner.

NLP, applied through the correct work took, could build data sets regarding suppliers, and decipher untapped information, due to language barrier. From a CSR or Sustainability & Governance perspective, NLP technology could streamline auditing and compliance actions previously unable because of existing language barriers between buyer-supplier bodies (greenbiz 2017).


  1. Q) Potential of AI in supply chain
  2. Q) Supply Chain Challenges implementing AI
  3. Q) Potential Threats

Power Of Block Chain Enable Supply Chain

Through blockchains, companies gain a real-time digital ledger of transactions and movements for all participants in their supply chain network. But don’t let the simplicity of the tool overshadow how transformational it is. The benefits to be gained will save you time, money, and effort on several fronts — and have the potential to redefine how you do business. Procurement: more visibility and more savings Companies negotiate procurement discounts based on the total number of purchases they drive. Your business may ask other people to do purchasing on your behalf, but the consequence is that it’s hard to keep track of the volume you drive across subsidiaries, business partners, and everyone else in your supply chain network. Blockchains make that simple. With a constantly refreshed digital ledger that incorporates data from all your relevant partners, your company can see the total volume regardless of who directed the purchase activity — without each user having to share its operational data with the others. Without a blockchain, companies hire many people to audit their orders to capture these volume-purchase benefits. Large businesses can have dozens of professionals spending days and nights to audit each one to add up all the gains they’re supposed to receive. But blockchains do this work without the staff and without any added time, eliminating the extra price-verification process. Data and analytics: better data, better outcomes The oldest phrase in computing is “garbage in, garbage out” — and nowhere does that apply more strongly and more expensively than in supply chain management. To compensate for uncertainty in how much product or material is in different locations — how much actual demand there has been in a period of time — companies put in extra inventory. And while that inventory is often cheaper than a lost sale, it’s far from free. In the technology industry, it is often estimated that keeping $1 of inventory costs 20 cents to 40 cents per year, when you account for both the cost of capital and the rapid depreciation of technology products.


Smart contracts to end costly procure-to-pay gaps The result is a ridiculous and insanely expensive dance as suppliers politely call and nudge customers to pay, while customers aim to cash in on the float by entering and processing invoices at a snail’s pace and occasionally “losing” them. Blockchains can put an end to that by integrating delivery and payment in digital contracts that flow across enterprises and integrate with logistics partners and banks. Using smart contracts, where the terms are payable upon receipt, a proof of delivery from a logistics carrier will immediately trigger automatic digital invoicing and payments through the banking system, with no analog gap between customer and supplier. The result has the potential to radically reduce working capital requirements and dramatically simplify finance operations, with a direct impact to the bottom line. Putting a stop to the rogues Blockchains give these supply chain networks the chance to create one shared truth without one all-powerful, centralised intermediary. Each participant has a copy of the ledger, and all transactions and movements are part of that ledger. If any participant tries to game the system or perpetrate fraud, that company is manipulating only its ledger and is immediately out of sync with the rest of the ecosystem, a powerful deterrent to bad behavior. Sounds good, right? So what’s the catch? You may be thinking that the blockchain is yet another “solution” in a long line of others you’ve purchased, and that you’re not ready to rip everything up and start again. The good news: you don’t have to. I’ll discuss how you can seize upon the supply chain of the future in the last article in this series.$FILE/ey-blockchain-and-the-supply-chain-three.pdf

IOT in Supply Chain

The process of assessing a chicken in real-time before agreeing to eat it may seem a bit outlandish. But with the IoT, we’ll be able to experience that type of transparency, and so much more. IoT is set to revolutionize the supply chain with both operational efficiencies and revenue opportunities made possible with just this type of transparency. In today’s market, supply chain isn’t just a way to keep track of your product. It’s a way to gain an edge on your competitors and even build your own brand.


With the ever advancing IOT we will be seeing changes in the following areas



Operational Efficiencies


When it comes to operational efficiencies, the IoT offers many:


Asset Tracking: Tracking numbers and bar codes used to be the standard method for managing goods throughout the supply chain. But with the IoT, those methods are no longer the most expedient. New RFID and GPS sensors can track products from floor to store. At any point in time, manufacturers can use these sensors to gain granular data like the temperature at which an item was stored, how long it spent in cargo, and even how long it took to fly off the shelf. The type of data gained from the IoT can help companies get a tighter grip on quality control, on-time deliveries, and product forecasting.


Vendor Relations: The data obtained through asset tracking is also important because it allows companies to tweak their own production schedules, as well as recognize sub-par vendor relationships that may be costing them money. Up to 65% of the value of a company’s products or services is derived from its suppliers. That’s a huge incentive to pay closer attention to how your vendors are handling the supplies they’re sending you, and how they’re handling your product once it’s made. Higher quality goods mean better relationships with customers—and better customer retention overall.

Forecasting and Inventory:  IoT sensors can provide far more accurate inventories than humans can manage alone. For instance, Amazon is using WiFi robots to scan QR codes on its products to track and triage its orders. All the data can be used to find trends to make manufacturing schedules even more efficient.

Connected Fleets: As the supply chain continues to grow—upward and outward—it’s even more imperative to ensure that all your carriers—be it shipping containers, suppliers’ delivery trucks, or your van out for delivery—are connected. Data is the prize. Just like cities are using this data to get to emergencies quicker or clear up traffic issues, manufacturers are using it to get better products to their customers, faster.

Scheduled Maintenance: The IoT can also use smart sensors on its manufacturing floors to manage planned and predictive maintenance and prevent down-time and cut costs.



Revenue Opportunities

The chance to know more—and understand more—about our customers, their buying habits, and the trends associated with them is invaluable. It allows businesses to form tighter connections with customers and, inevitably, market to them in new and better ways. Beyond the use of data for improved efficiencies noted above, businesses can get creative with supply chain transparency. They can build a reputation of social responsibility by allowing customers to access—and with AR, even see—where their product came from, who made it, and the conditions in which those workers lived.

Research shows 70% of retail and manufacturing businesses have already begun to transform their supply chain processes. However, when it comes to supply chain, there is far from a level playing field. For the IoT to be truly effective, all members of one’s global supply chain must be connected. In an age when many companies are just now embracing the concept of mobility, that may take a while. Still, as technologies like blockchain and edge computing continue to take form, there is so much further we can go to make our supply chain even more efficient—and creative—than ever before. Perhaps that’s where the real excitement lies.


Q) When will IOT really begin to have an impact on supply chain operations?

Q) What are the other opportunities and applications of IOT in supply chain?

Q) What are the major challenges faced by companies in implementing IOT in supply chain?