Artificial Intelligence (AI) in Supply Chain Planning: The Future is Here & Now

leadership development coaching

By Mark Balte

According to a recent International Data Corporation (IDC) Digital Economy Model, by 2023 over 50% of all worldwide nominal gross domestic product will be driven by digitally transformed enterprises. And, by 2025, at least 90% of new enterprise apps will have embedded AI capabilities.1 Gartner estimates that by 2021, AI augmentation will generate $US2.9 trillion in business value and recover 6.2 billion hours of worker productivity.2 In study after study, there is evidence of the growing use of AI across all business functions, including the supply chain. Yet, with all of the fervor and excitement around AI, many don’t fully understand what it is and how it can help improve operations including margin growth, service levels and risk mitigation.

This article discusses the importance of embracing Artificial Intelligence (AI) in supply chain planning operations and why the best time to embrace AI capabilities is right now. We will explore the capabilities available today to help you improve productivity, accuracy and speed as well as explore some of the technologies companies are working on today that will power the supply chain of tomorrow.


The Future is Now

AI helps organisations overcome the shortage of supply chain talent. Some experts estimate that there is only one qualified supply chain planner/analyst for every six openings.

The phrase digital transformation is all around us and many companies have embarked on their journeys to digitise their business. However, it is critical to realise that access to data alone does not equate to insight or value. Humans have a limited ability to understand what data is important and to conduct the analysis necessary to quickly make the right decisions. The ongoing challenges to attract and retain talent, meet rising customer expectations and stay ahead of fierce competition and pricing pressures means companies are missing opportunities for improved margins, reduced working capital investments and greater service levels. The convergence of increased data availability and technology advancements, makes the time right to embrace an AI-powered supply chain as we can now uncover key insights from the terabytes of data available to us.

AI helps organisations overcome the shortage of supply chain talent. Some experts estimate that there is only one qualified supply chain planner/analyst for every six openings. To make matters worse the most experienced workers, those currently between 55 and 75 years of age, are retiring at a rate of 10,000 every day. AI enables the capture of knowledge, the automation of repeatable processes and the augmentation of complex decision making to smooth the transition to Generation Z, those born after 1997, who are now entering the workforce. This generation, we call “Digital Natives,” have grown up always connected with access to anything and everything at a moment’s notice. Digital Natives expect the same AI empowered experience at work as they have in their personal lives. To attract the best and brightest Generation Z candidates, companies need to embrace advanced technologies including AI.

Customer expectations for low cost, high quality and instant availability drives the need to compress time throughout the entire supply chain from product design to customer availability. AI enables time-compression through automation, augmentation and the ability to make better decisions faster. Companies that don’t significantly accelerate process times may be at a serious competitive disadvantage.

Finally, today’s high-powered and inexpensive computers enable advanced supply chain solutions that could only be dreamed about a few years ago. Think of all the power Google Assistant or Amazon Alexa brings to you every day? Now, imagine that built for the rigors of the enterprise powering your operations.

Here are just a few of the AI-powered capabilities available to you today:

Optimised Forecast Algorithm Selection automatically selects the best forecast algorithm whenever new data is added to demand history. It is fairly common today for companies to select an algorithm (or two) and stick with it across a product’s entire life-cycle. The algorithms are rarely reviewed or updated. Leading companies use what is commonly referred to as a ‘Best-Fit’ algorithm. This AI powered capability automatically compares the forecast accuracy for every item across all available forecast algorithms, and chooses the algorithm that minimises forecast error. ‘Best-Fit’ forecast algorithm selection ensures that forecast accuracy is optimised throughout the product life-cycle.

Forecast Parameter Optimisation continuously senses, analyses and updates forecast planning parameters used for trend, seasonality, smoothing, etc. to improve forecast accuracy and ensure the supply chain operates at peak performance. Often these parameters are set during the initial implementation of a supply chain solution and left alone because valuable resources are focused on the day-to-day supply chain operation. This is a significant untapped opportunity for the majority of supply chains. Logility PulseWise™, for example, is an AI-driven solution that autonomously analyses demand signals against actual performance to proactively adjust forecast algorithm parameters. By removing the need for human interaction, the vital adjustments can be made leading to 20 percent or more accuracy improvements.

Demand Outlier Adjustment capabilities automatically detect anomalous demand history data points and substitutes a corrected value. A great amount of time and effort can be spent correcting and adjusting data history to account for anomalies due to stock outs, competitor actions, unplanned disruptions or non-repeating events. Using machine learning we can now analyse both uncorrected and corrected forecasts to ‘learn’ what bad data looks like and make substitutions for anomalies that improve forecast accuracy. An AI powered demand outlier adjustment solution reduces time spent on history data manipulation, freeing up planner time to work on more value-adding activities.

Demand Sensing from Unstructured Data capabilities use machine learning pattern recognition and natural language processing to read and analyse ‘Big Data’ to recognise complex patterns and provide data insights. In today’s social media driven economy, consumer likes and wants can shift very quickly. It is nearly impossible for planners and analysts to stay abreast of all the latest social media data when all it takes is a celebrity tweet about their favorite product to spike demand. Advanced solutions like that available from Logility automatically analyse terabytes of unstructured data to determine “sentiment” and quickly predict an impact on short and longer-term demand.

Probabilistic Demand Simulation uses machine learning to understand forecast variability at the record level. In contrast to single-valued forecasts, probabilistic demand simulation builds a range of possible demand forecasts. Advanced solutions use this understanding of variability to create randomised forecasts which are used in n-tiered, supply constrained ‘Digital Twin’ simulations to predict supply chain resilience. The incorporation of product level revenue and profit information into these Monte Carlo type simulations enables a risk assessment of meeting both volumetric and financial targets within the expected range of demand probabilities.

An AI powered demand outlier adjustment solution reduces time spent on history data manipulation, freeing up planner time to work on more value-adding activities.

As the saying goes, bad data in leads to bad data out. If the information you use to generate plans has errors, the accuracy and efficacy of those plans will be severely compromised. Automatic Data Cleansing and Parameter Population uses machine learning to recognise incomplete or inaccurate data and either automatically applies the correct data or alerts the appropriate data manager to take corrective action. Advanced solutions such as Logility AdapLink™ automatically cleanse data and populate supply chain parameters to ensure timely and accurate data is available for supply chain planning operations.


The AI Crystal Ball

IDC forecasts that spending on AI and machine learning will grow from $8B in 2016 to $47B in 2020.1 According to Gartner, “The deployment of AI has tripled in the past year – rising from 25 percent in 2018 to 37 percent today.” Gartner states, “The reason for this big jump is that AI capabilities have matured significantly and thus enterprises are more willing to implement the technology.”4 AI is being deployed and it will significantly change the way company’s plan and manage their supply chains. Today’s innovative solution providers are actively developing new AI powered capabilities that automate planning operations and augment planner capabilities. Here are a few AI capabilities you should keep an eye on and evaluate how they can fit into your operations.

Cognitive Analytics, the most advanced type of analytics, enable users to identify ‘New Insights’ through the use of AI, Machine Learning, and Natural Language Processing. Cognitive analytics enable autonomous analysis and response to free up valuable resources to work on more value-adding activities. Additional cognitive analytic capabilities are being developed to automatically sense, analyse and respond to unplanned disruptions and opportunities helping to minimise risk and maximise company benefits.

Scenario Selection Augmentation utilises advanced cognitive capabilities to develop new insights and augment a planner’s ability to make well-informed and decisions fast. ‘What-if’ scenario analysis can help analyse tradeoffs and make better decisions. However, identifying the right information to make a decision can be difficult and building ‘what-if’ scenarios can be time-consuming. AI powered scenario selection augmentation can autonomously search for the best solutions for disruptions and opportunities and provide the planner with a set of the best alternatives to accelerate decision making.

Demand for new products is often difficult to forecast. Product Life-Cycle Profile Optimisation improves forecast accuracy for items through AI powered attribute-based modeling techniques. Attribute-based modeling involves creating demand profiles, assigning a profile to a new item, ongoing accuracy assessments and automatic profile revisions. Product life-cycle profile optimisation solutions learn from previous product introductions to optimise the profile shape and volume for new product launches.

Supply Parameter Optimisation continuously senses, analyses and updates supply planning parameters to improve supply optimisation and help ensure the supply chain operates at peak performance. As on the demand side, supply planning parameters are rarely reviewed or adjusted to reflect the actual state of the physical supply chain. This AI powered capability autonomously analyses the current supply chain state against supply planning parameters populated in the supply chain ‘digital twin’ to automatically update these parameters to optimise supply chain response.

Probabilistic Supply Simulations is an advanced AI powered capability to understand variability in supply capacity to build a range of possible supply responses. Randomised supply capacities are used when running simulations on product level revenue and profit data which can be incorporated to enable risk assessment in financial terms within the expected range of supply possibilities.

The first wave of Gen Z’s are entering the workforce and they expect to have the same Natural Language Interface capabilities available to them in the workplace that they grew up with. Advanced solution suppliers are developing natural language interfaces that will allow the users to converse with their platform as easy as we converse with mobile devices and home assistants today.



Artificial intelligence is a software that learns, analyses and adapts as new data is absorbed. AI solutions can understand complex concepts, solve complex problems and make complex decisions. Some forms of AI mimic the human brain, learning and evolving over time. According to Supply Chain Insights, “CEOs expect supply chain leaders to prepare for digital business and want to know how they intend to develop capabilities and use advanced technologies like artificial intelligence to create a flexible, agile and responsive digital supply chain.”3

As business leaders, here are a few ways you can help your supply chain team get started with AI:

• Identify the big problems you want to solve and the big opportunities you should embrace. These problems and opportunities might be areas where AI could make a significant impact within your company.

• Provide your team the opportunity to do their research and learn what benefits AI capabilities provide to other companies.

• Empower your team to start now with purpose-built and embedded AI solutions. Measure results to build the business case for more AI powered solutions. Encourage your teams to explore the current solutions they have in place; chances are there are AI capabilities available that are not fully utilised.

• Most importantly, focus on your talent. Train them, let them build experience and pursue areas where AI can add value.

The introduction of AI into supply chain operations can propel your business into the future– harnessing automation, optimising supply chain planning, and evaluating multiple scenario outcomes to boost your confidence in decision-making. Building a strong foundation of people, process, data and solutions, and taking advantage of purpose-built, industry-leading supply chain technologies, like those offered by Logility, can build your expertise and accelerate your move up the AI maturity curve. Imagine saying, “OK Logility, how’s my supply chain?” and the system informing you of all potential issues, what the system has already implemented and then to provide a list of prioritised items which require your attention. That’s a powerful future.

About the Author

As Executive Vice President of Research and Development, Mr. Mark A. Balte is responsible for all product development and technology strategies for the Logility digital supply chain platform. His leadership and creativity are crucial to driving innovation in Logility’s cloud strategy, product architecture, advanced analytics, and mobility. Mr. Balte has more than 30 years of experience in developmemt,  implementation and support of supply chain software solutions.

Mr. Balte holds a Bachelor of Science degree in Mathematics from The University of the South (Sewanee) and Master of Science degree in Operations Research from the Georgia Institute of Technology. He is a frequent guest lecturer of the supply chain management graduate program at the Gorgia Institute of Technology.

1. Worldwide IT Industry 2020 Predictions: IDC FutureScape, Frank Gens, SVP & Chief Analyst, October 29, 2019
3. CEO’s expectations for artificial intelligence in the supply chain – Supply Chain Insights; Gartner Research 2018 – 2019
4. – 21 – gartner-survey-shows-37-percent-of-organizations-have


Please enter your comment!
Please enter your name here