What is the role of Artificial Intelligence in Supply Chains?

The network-based nature of supply chains and logistics creates suitable conditions where to implement AI. AI is a powerful set of tools to help transition supply chain operations

• from reactive to proactive,

• from manual to autonomous processes,

• fromstandardised to personalised processes,

• from forecasting to prediction and prescription of supply chain planning.

According to Gartner Researcher Noha Tohamy, the use of AI in supply chains can be of two kinds:

• “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”

The activities where these AI application can be felt in Supply Chains include:

• Chatbots for operational procurement, task automation, or status delivery

• Machine Learning for Planning

• Machine learning for Warehouse Management

• Autonomous vehicles for logistics and shipping

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

• ML and Predictive Analytics for Supplier Selection and Supplier Relationship Management (SRM)

 A number of different AI techniques have been used in Supply Chains, such as:

• ANN (Artificial Neural Networks), an information-processing technique that can be used to find patterns, knowledge or models from an extensive amount of data. In supply chains it has been used in sales forecasting, marketing DSSs, pricing and customer segmentation to production forecasting, supplier selection, demand management and consumption forecasting.

• FL/Modelling, for developing complicated models and systemsthrough an approach that addresses qualitative information to resemble the manner in which humans make inferences and decisions

• ABS (agent based simulation) and MAS (Multi-agent systems), simulates the actions and interactions of autonomous agents, either collectively or individually, while considering the assessment of their influences on the system in general. These have been used in distributed supply chain planning, design and simulation of supply chain systems, analysis of the complex behaviour of supply chains, and negotiation-based collaborative modelling

• GA (Genetic Algorithms) a search technique mimicking natural selection, in which the algorithm evolves to the point at which it has adequately solved the problem. This technique has been used in : multi-objective optimisation of supply chain networks, partner selection in green supply chain problems, multi-product supply chain networks, and the problem-solving approach to closed-loop supply chains.

• Data mining, stimulated by the growth of gigantic operational databases that could provide insight into decision-making and other processes. Data mining has been used for controlling and monitoring warehouses, food supply chains and sustainability in supply chains, improving knowledge management and marketing, and enhancing supply chain innovation capabilities

• CBR (Case-based reasoning), a technique based on the cognitive psychological notion that humans find their knowledge through solving multiple problems. CBS has been used in designing mechanisms for supply chains under demand uncertainties, supply chain risk management, supplier performance evaluations, agile Supply Chain Management, and supply chain negotiations

• Swarm Intelligence, which uses the behaviour of social insects by determining their efficiency at solving complicated problems. In Supply Chains it has been used in: designing of systems for pricing, product line optimisation, inventory replenishment, supply chain network architecture optimisation, and minimisation of supply chain costs, and the designing of agile supply chain networks

• SVM (Support Vector Machines), a technique that is capable of deciphering subtle patterns in noisy and complex data sets by using clasifiers. In supply chain management, it has been used in: supply chain demand forecasting, time-series classification in supply chains, supplier selection, and for the design of supply chain networks