MODULE - 5 AI and ML for Inventory and Supply Chain Excellence

STRUCTURE
5.1 Introduction
5.1.1 Key Challenges in the Supply Chain
5.1.2 Benefits of Machine Learning in Supply Chain
5.2 Machine Learning Use Cases in the Supply Chain
5.3 ML for Supply Chain Management: How to make it work
5.4 Summary
5.5 Keywords
5.6 Self-Assessment Questions

LEARNING OUTCOMES
1. Understand how Supply Chain Management be made effective.
2. Describe Machine Learning Use Cases in the Supply Chain
3. Identify how ML will work for Supply Chain Management.

5.1 INTRODUCTION
How can supply chain management be made effective? Many makers, retailers, distributors, and
suppliers are unsure of the answer to this. Businesses are pondering how to make their supply chain
less susceptible to disruption in the current environment of shifting supply chain market dynamics,
evolving workplace practices, and increasingly volatile demand. Many well-known and new supply
chain problems can be solved by machine learning.
There are numerous applications of machine learning in the supply chain. The advantages of machine
learning and artificial intelligence (AI) can be found throughout the supply chain, including
procurement, manufacturing, inventory management, warehousing, logistics, and customer support.
Let's delve deeply into the benefits of machine learning in supply chain management and supply
chain machine learning use cases.

1
5.1.1 Key Challenges in the Supply Chain

Companies can use machine learning to improve their supply chain management, making it more
resilient to potential disruptions. Global supply chain markets struggle with uncertainty, fragility and
lack of transparency. According to Körber's recent Supply Chain Complexity study, only one in ten
companies can stay ahead of their supply chain challenges. In addition to increasing customer
expectations, lack of visibility and operational complexity, companies today face unique challenges:
transportation issues, remote work, shortages due to unexpected growth in demand, etc. According
to McKinsey, there are five main sources of vulnerability in a company. supply chain caused by the
pandemic. And supply chain learning use cases are a ready blueprint for where supply chain
professionals should start solving big supply chain problems.

We have all witnessed the transformation of the conventional linear supply chain into digital supply
networks in recent years. (DSNs). COVID-19 has only accelerated this process, forcing businesses
to reconsider their worldwide supply chain strategies in light of the new reality. It is possible to
transform conventional, linear supply chains into connected, intelligent, scalable, and customizable
digital supply networks using technologies such as IoT, artificial intelligence, and machine learning.
2
"Traditional supply networks adhere to predetermined, precise workflows, doing A, B, and C in that
order. Most industrial execution systems operate in this manner. In contrast, a nondeterministic
system has workflows that aren't predetermined and automation that can manage business rules in a
variety of ways. Enhanced digital manufacturing solutions can reorganize and optimize production
processes, prevent unscheduled downtime, and lower the costs associated with switching product
lines. - Forrester Research Inc., Automate Your Supply Chain With Its Automation Framework,
January 13, 2020

5.1.2 Benefits of Machine Learning in the Supply Chain

Retailers, suppliers, and distributors can create the transformational changes that are so desperately
required right now in the face of the pandemic thanks to machine learning use cases in the supply
chain. Machine learning provides supply chain operations with value that has never before been
possible, including cost savings from decreased operational overhead and risk mitigation, improved
supply chain forecasting, quick deliveries, and enhanced customer support, to name a few.
According to McKinsey, the biggest advantages of machine learning will be in giving supply chain
professionals deeper understanding of how to improve supply chain performance and foreseeing
anomalies in logistics expenses and performance before they happen. Machine learning is also
revealing which areas of automation will result in the greatest scale benefits.

Fig: Advantages of ML in Inventory & Supply chain

3
 5.2 MACHINE LEARNING USE CASES IN THE SUPPLY CHAIN

Retailers and suppliers are working in a completely new way as a result of supply chain machine
learning applications. Machine learning, a subfield of artificial intelligence, trains a computer model
with data so that it can respond to changing circumstances without being explicitly designed to do
so. In this manner, the machine can gradually train itself, enhancing the precision of its own
algorithms. There are a number of machine learning methodologies used in the supply chain.
According to Gartner, by 2023, 25% of all supply chain technology solutions will include embedded
or enhanced intelligent algorithms and AI techniques.

In the supply chain, there are eight different types of machine learning use cases.

 Inventory Management:
4
Storing and maintaining inventory in a good condition is costly. Therefore, inventory planning
should be approached carefully by supply chain professionals as it directly affects a company's cash
flow and profit margins. One of the most prevalent applications of machine learning in the supply
chain is inventory management. The issue of under- or overstocking can be resolved with the aid of
machine learning. With machine learning (ML), you can forecast the growth of demand based on
information from a variety of sources, including the marketplace environment, seasonal trends,
promotions, sales, and historical analysis. Additionally, you can plan ahead to stock up on supplies
and avoid having an excess of either goods or crucial components for manufacturing.

You need a large amount of data to make an accurate forecast. When the number of data sets is not
sufficient for effective analysis, machine learning offers several methods to solve the problem:

• Data augmentation makes it possible to greatly increase the variety of data available in training
models without actually collecting new data. Augmentation techniques used in deep learning
applications depend on the data type. Techniques such as SMOTE or SMOTE NC are popular for
adding purely numerical information. For unstructured data such as images and text, augmentation
methods vary from simple transformations to data generated by neural networks, depending on the
complexity of the application.

• Incremental learning is a machine learning method that does not require a large amount of data to
train a model. Instead, learning starts with a very simple model that typically predicts the mean with
some deviation. As the data scientist inputs new data samples, the model is trained to predict more
accurate results. Over time, the number of data sets will be good enough to make reliable predictions.

• Reinforcement learning is one of the three basic machine learning techniques along with supervised
and unsupervised learning. It uses rewards and punishments as signals for positive and negative
behavior. In robotics and industrial automation, RL is used to enable a robot to create an efficient
adaptive control system for itself that learns from its experiences and behavior.

When it comes to data, the question arises of which data storage solution to choose.
Data warehouse or data lake. Data lakes are often used as part of machine learning or advanced
analytics solutions. It is commonly used in ML projects because it can collect data from multiple
sources in real time and store it in its native format. Data lakes are ideal for deep analysis of large
areas of data collected over time, while data warehouses are best suited for operational processes
and day-to-day activities. However, many companies today use both storage options. Especially
when building a data warehouse on top of a data lake and using data from the cleaned and structured
DL.

Another example of ML application in supply chain is for computer vision (CV) in inventory
management. Widely used in various ways. First, it applies to counting and sorting incoming items.
CV is also useful in detecting visible damage to packages. Using computer vision, software can also
classify the objects it "sees." For example, a camera-equipped robot inspects a warehouse and
automatically creates a real-time image of inventory. CV is one of the areas where all kinds of
machine learning techniques (supervised learning, unsupervised learning, reinforcement learning)
can be applied.

5
 Warehouse Management:

Warehouses use machine learning to automate manual work, predict potential problems and reduce
paperwork for warehouse staff. For example, computer vision can be used to monitor the operation
of a conveyor belt and predict when it will jam. NLP and OCR allow warehouse experts to
automatically detect the arrival of packages and change their delivery statuses. The cameras scan the
barcodes and labels on the package, and all the necessary information goes directly to the system.

Machine learning can also help program self-driving cars and robots that are widely used in
warehouses. With the help of guides built into the system, self-driving cars and robots assist in
receiving, packing/unpacking, transporting, and loading/unloading boxes. Computer vision, in this
case, can help find empty bin locations, control whether bins are placed correctly, and prevent
collisions between robots and vehicles in the warehouse.

One of our customers, a German-based Fortune 100 multinational engineering and technology
company, needed to streamline the management of over 400 warehouses worldwide. We worked
with N-iX specialists to modernize and build a scalable logistics platform. The solution is in the
development stage. N-iX is working on computer vision solutions for warehouse-mounted cameras
based on industrial optical sensors and lenses, and Nivida Jetson devices. The solution allows
customers to automatically recognize incoming packages, scan barcodes, and change the delivery
status of boxes. Also, our team is responsible for developing a mobile multi-platform CV app. This
product assists the customer with his OCR and NLP of object detection, package damage detection,
and document processing. Our modernized and scalable logistics platform significantly improves
warehouse efficiency in over 60 countries, reducing operating costs and warehouse downtime.

 Logistics & transportation:

ML helps understand where a package is in the entire logistics cycle. It allows force chain
professionals to track the position of goods during transportation. Also, it provides visibility into the
conditions under which the package is being transported. With the help of detectors, retailers can
cover similar parameters as moisture, vibration, temperature, etc. Besides, ML helps with real-time
route optimization. It tracks rainfall and road conditions and gives recommendations on how to
optimize the route and reduce driving time. This way, exchanges can be diverted at any time on their
way when a more cost-effective route is possible.

 Production:

ML enables early detection of quality issues in line production. With the help of computer vision,
manufacturers can, for example, check whether the final appearance of their products meets the
required quality level. If the product is defective, it can be easily detected before it reaches the
customer. One of the other widespread use cases for machine learning in the supply chain is
predictive maintenance of equipment. ML ensures reactive and preventative maintenance of
equipment based on real-time asset data rather than predefined calendars. By improving asset
maintenance, supply chain professionals can significantly reduce maintenance costs. ML also helps
reduce the number of no fault found (NFF) cases. NFF is a decommissioned unit following

6
 complaints about recognized equipment failures. If no anomalies are detected, the unit is returned to
service without repair. The fewer such accidents, the more efficient the manufacturing process.

 Chatbots:

Intelligently independent chatbots powered by machine learning technology are trained to

understand specific keywords and phrases that trigger bot responses. They are commonly used in
supplier relationship management, sales, and supply management to help employees focus on value-
added tasks instead of getting frustrated answering simple questions. Over time, they train
themselves to understand more questions—learn and train from experience.
For example, write to your chatbot: "There is a problem sending the package". The bot understands
the words "problem", "delivery" and "package" and provides predefined answers based on these
phrases.

 Customer Services:

Consumers expect up-to-date information on delivery status. Thanks to ML, it is possible to predict
the delivery of packages, taking into account all changing conditions. As a result, consumers get a
stronger customer experience with more accurate delivery date forecasts. Machine learning enables
retailers to:

 Identify packages at risk of problems and suggest corrective actions

 Automate notification flows based on past consumer interactions

 Determine when to communicate with consumers to maximize engagement

Machine learning technology also enables the company to deliver a superior customer experience.
ML does this by enabling the business to gain insight into the correlation between product
recommendations and subsequent customer visits to her website.

 Security:

Machine learning algorithms can dissect huge quantities of data and draw patterns for every business
to cover it from fraud. For cases, in the force chain, ML helps identify fraudulent deals, help
credential abuse, accelerate fraud examinations, and automate anti-fraud processes. also, with ML,
force chain professionals can automate the process of covering whether all corridors as well as
finished products meet the quality or safety norms.

 Business:

From a business perspective, machine learning provides valuable insights that simplify and
accelerate decision-making. This allows management to quickly assess best-case and worst-case
scenarios. Machine learning uses complex algorithms to suggest optimal solutions to management
7
and help them make informed decisions.

For instance, stock level analysis can tell when a product's appeal is waning and its shelf life is
approaching in the store sector. Price analysis can be used to determine the best balancing act
between pricing and customer demand by comparing it to supply-chain expenses and retail profit
margins.

5.3 ML FOR SUPPLY CHAIN MANAGEMENT: HOW TO MAKE IT WORK

There are three important steps you should take to adopt machine learning in supply chain
management. As follows:

1. Recognize the layout of your supply network:

Before implementing machine learning into your supply chain, you should evaluate your complete
supply chain's structure:
• Identify the essential elements of your business.
• Perform a thorough study of the supply chain, including Tier 1 and lower-tier suppliers.
• Find nodes of connectivity and hidden connections.
• Analyze the supply chain's relative vulnerability quantitatively.
• Recognize supply chain risk factors and obstacles.
• Make insightful comparisons with business benchmarks and peers.
• Evaluate the delivery chain's security.
• Compare the process, people, and technology to your functional development.

2. Creating transparent company KPIs and calculating ROI

You need to conduct a Discovery Phase and calculate ROI to understand under what conditions
machine learning use cases in your supply chain would be beneficial to your company. You must
calculate TCO and the revenue you will achieve over the short- and long-terms.
Additionally, it's crucial to create a thorough strategy outlining your objectives and the steps
necessary to achieve them. Aligning company KPIs with machine learning KPIs is essential to
removing inconsistencies. In other words, you must describe the business issue in terms of machine
learning.

3. Making sure the ML engineering method is efficient

The following factors are crucial to the success of supply chain machine learning use cases:
• Create a multidisciplinary team of experts with backgrounds in business analysis, Python, DevOps,
Python, and data science.
• State the business issue first.
• Decide on the appropriate success measures.
• Select the appropriate tech mix.
• Take into account your data availability; pay attention to data volume and quality.
• Create, evaluate, train, and improve models.
• Retrain and deploy models.
• Keep track of model success.

8
5.4 SUMMARY
AI and ML revolutionize inventory and supply chain management by enabling accurate demand
forecasting, optimizing supplier relationships, enhancing replenishment strategies, and
proactively mitigating risks. These technologies drive efficiency, reduce stock outs, minimize
excess inventory, and improve overall supply chain performance, empowering businesses to
achieve excellence in operations and maintain a competitive edge in dynamic markets.

5.5 KEYWORDS

AI (Artificial Intelligence) refers to the development of computer systems that can perform tasks
that typically require human intelligence, such as problem-solving, decision-making, and learning
from data.

ML (Machine Learning) is a subset of AI that focuses on creating algorithms and models that
enable computers to learn and improve from experience, without being explicitly programmed.

SCM (Supply Chain Management) involves the planning, coordination, and optimization of
various processes involved in the flow of goods, information, and finances across a network of
suppliers, manufacturers, distributors, retailers, and customers.

EMS (Efficient Manufacturing Systems) refers to the implementation of processes, technologies,

and strategies that enhance the productivity, quality, and cost-efficiency of manufacturing
operations.

DSS (Decision Support Systems) are computer-based tools that assist individuals or organizations
in making informed decisions by analyzing data, providing insights, and presenting alternative
scenarios.

ERP (Enterprise Resource Planning) is a software system that integrates and manages various
core business processes, such as finance, human resources, procurement, and inventory, within a
single unified platform.

DRP (Distribution Requirements Planning) is a system that helps organizations manage and
optimize the distribution of products to meet customer demands while minimizing inventory and
storage costs.

RFID (Radio Frequency Identification) is a technology that uses radio waves to track and identify
objects equipped with RFID tags, allowing for real-time monitoring and data collection.

IoT (Internet of Things) refers to the network of interconnected physical devices, vehicles,
buildings, and other objects embedded with sensors, software, and connectivity, enabling them to
collect and exchange data.

S&OP (Sales and Operations Planning) is a process that aligns an organization's sales and
operational teams to develop a unified plan, optimizing resources and ensuring that production meets
demand while balancing costs.

9
ROI (Return on Investment) is a performance metric used to evaluate the profitability or efficiency
of an investment, indicating the ratio of the net profit gained relative to the initial cost of the
investment.

KPIs (Key Performance Indicators) are quantifiable metrics used to assess the success of an
organization, department, or project by measuring progress toward specific goals and objectives.

5.6 SELF-ASSESSMENT QUESTIONS

Long questions
1. Explain Key challenges in Supply Chain Management.
2. Elaborate different ML Use Cases in Supply Chain.
3. How ML will work with Supply Chain? Explain with an example.
4. Write a note on inventory management using AI/ML.
5. Explain the role of AI/ML in Security of Supply Chain Management.
6. Write a note on warehouse management using AI/ML.

Short questions
1. How has AI and ML transformed inventory management and supply chain operations?
2. What specific AI techniques enhance demand forecasting accuracy?
3. How do ML models optimize supplier relationships in supply chain management?
4. How does AI proactively manage supply chain risks?
5. What are the key stages in implementing ML for supply chain excellence?
6. How have AI and ML improved customer satisfaction and revenue?

Fill in the blanks

1. AI and ML technologies have revolutionized inventory management by enabling

____________ and ____________ demand forecasting, leading to better alignment of stock
levels with market needs.
2. In supply chain management, ML models predict supplier performance based on
____________ behavior, aiding in optimal sourcing decisions.
3. One of the key benefits of AI in supply chain excellence is its ability to identify and mitigate
potential supply chain ____________ using real-time data and predictive analytics.

10
4. The integration of AI and ML in inventory and supply chain management requires high-quality
and ____________ data for accurate predictions and insights.
5. The stages of AI implementation for supply chain excellence include data ____________,
model ____________, integration, testing, and employee ____________.
6. AI-driven risk assessment tools enable proactive identification of potential ____________
events that could disrupt the supply chain, allowing for timely mitigation.

True/ False
1.ML models can predict supplier performance based on historical data, helping optimize sourcing
decisions.
2.AI-powered risk assessment tools cannot identify potential disruptions in the supply chain.
3.The stages of AI implementation for supply chain excellence include data integration, model
integration, and employee training.
4.AI and ML cannot help in optimizing supplier relationships within the supply chain.
5.AI and ML do not contribute to enhancing overall supply chain resilience and competitiveness.
6.AI and ML have no impact on customer satisfaction and revenue growth in supply chain
operations.

Multiple choice question

1. What is the primary benefit of using AI and ML for demand forecasting in inventory
management?
a) Reducing supplier lead times b) Minimizing excess inventory c) Increasing order quantities d)
Decreasing stockouts
2. Which technology enables ML models to predict supplier performance and optimize sourcing
decisions?
a) Artificial Neural Networks (ANN) b) Radio Frequency Identification (RFID) c) Enterprise
Resource Planning (ERP) d) Computer-Aided Design (CAD)
3. How does AI contribute to proactive risk management in the supply chain?
a) By eliminating all potential risks b) By predicting and mitigating potential disruptions c) By
focusing only on external risks d) By reducing the need for risk management
4. What is the role of clean and accurate data in AI and ML implementation for supply chain
excellence?

11
a) It is not important for AI and ML. b) It ensures that AI models have no impact on the supply
chain. c) It is essential for accurate predictions and insights. d) It only impacts employee training.
5. Which stage is NOT typically part of the AI implementation process for supply chain
excellence?
a) Data collection b) Model development c) Supplier negotiations d) Employee training
6. How do AI and ML impact supplier relationships within the supply chain?
a) They have no effect on supplier relationships. b) They optimize supplier selection and
collaboration. c) They create barriers in communication with suppliers. d) They focus only on
demand forecasting.

Match the following

Question 1: Arrange the following stages of AI implementation for Supply Chain Excellence in the
correct order:
a) Data Collection b) Model Development c) Integration with Existing Systems d) Employee
Training e) Testing and Validation
Question 2: Arrange the following benefits of AI and ML implementation for Inventory and Supply
Chain Excellence in the correct order:
a) Enhanced Supplier Relationships b) Improved Demand Forecasting c) Proactive Risk
Management d) Replenishment Optimization e) Reduction in Stockouts
Question 3: Arrange the following steps in the AI-driven Replenishment Optimization process in
the correct order:
a) Calculate Optimal Reorder Quantities b) Analyze Demand Variability c) Determine Optimal
Reorder Points d) Consider Lead Times e) Minimize Excess Inventory
Question 4: Arrange the following components of AI-powered Supplier Management in the correct
order:
a) Supplier Performance Prediction b) Historical Data Analysis c) Optimal Sourcing Decisions d)
Supplier Collaboration e) Supplier Relationship Optimization
Question 5: Arrange the following steps of AI-driven Risk Management in the correct order:
a) Early Detection of Disruptions b) Predictive Analytics c) Identification of Potential Risks d)
Mitigation Strategies e) Real-time Data Analysis

Answer keys
Fill in the blanks
12
1. AI and ML technologies have revolutionized inventory management by enabling
____________ and ____________ demand forecasting, leading to better alignment of stock
levels with market needs.
Answer: accurate, data-driven
2. In supply chain management, ML models predict supplier performance based on
____________ behavior, aiding in optimal sourcing decisions.
Answer: historical
3. One of the key benefits of AI in supply chain excellence is its ability to identify and mitigate
potential supply chain ____________ using real-time data and predictive analytics.
Answer: disruptions
4. The integration of AI and ML in inventory and supply chain management requires high-quality
and ____________ data for accurate predictions and insights.
Answer: clean
5. The stages of AI implementation for supply chain excellence include data ____________,
model ____________, integration, testing, and employee ____________.
Answer: collection, development, training
6. AI-driven risk assessment tools enable proactive identification of potential ____________
events that could disrupt the supply chain, allowing for timely mitigation.
Answer: disruptive

True / False
1.ML models can predict supplier performance based on historical data, helping optimize sourcing
decisions.
Answer: True
2.AI-powered risk assessment tools cannot identify potential disruptions in the supply chain.
Answer: False
3.The stages of AI implementation for supply chain excellence include data integration, model
integration, and employee training.
Answer: False
4.AI and ML cannot help in optimizing supplier relationships within the supply chain.
Answer: False
5.AI and ML do not contribute to enhancing overall supply chain resilience and competitiveness.
Answer: False
6.AI and ML have no impact on customer satisfaction and revenue growth in supply chain
13
operations.
Answer: False

Multiple Choice :
1. What is the primary benefit of using AI and ML for demand forecasting in inventory
management?
a) Reducing supplier lead times b) Minimizing excess inventory c) Increasing order quantities d)
Decreasing stockouts
Answer: d) Decreasing stockouts
2. Which technology enables ML models to predict supplier performance and optimize sourcing
decisions?
a) Artificial Neural Networks (ANN) b) Radio Frequency Identification (RFID) c) Enterprise
Resource Planning (ERP) d) Computer-Aided Design (CAD)
Answer: a) Artificial Neural Networks (ANN)
3. How does AI contribute to proactive risk management in the supply chain?
a) By eliminating all potential risks b) By predicting and mitigating potential disruptions c) By
focusing only on external risks d) By reducing the need for risk management
Answer: b) By predicting and mitigating potential disruptions
4. What is the role of clean and accurate data in AI and ML implementation for supply chain
excellence?
a) It is not important for AI and ML. b) It ensures that AI models have no impact on the supply
chain. c) It is essential for accurate predictions and insights. d) It only impacts employee training.
Answer: c) It is essential for accurate predictions and insights.
5. Which stage is NOT typically part of the AI implementation process for supply chain
excellence?
a) Data collection b) Model development c) Supplier negotiations d) Employee training
Answer: c) Supplier negotiations
6. How do AI and ML impact supplier relationships within the supply chain?
a) They have no effect on supplier relationships. b) They optimize supplier selection and
collaboration. c) They create barriers in communication with suppliers. d) They focus only on
demand forecasting.
Answer: b) They optimize supplier selection and collaboration.

14
Match the following
Question 1: Arrange the following stages of AI implementation for Supply Chain Excellence in the
correct order:
Answer: a) Data Collection b) Model Development e) Testing and Validation c) Integration with
Existing Systems d) Employee Training
Question 2: Arrange the following benefits of AI and ML implementation for Inventory and Supply
Chain Excellence in the correct order:
Answer: b) Improved Demand Forecasting d) Replenishment Optimization e) Reduction in
Stockouts a) Enhanced Supplier Relationships c) Proactive Risk Management
Question 3: Arrange the following steps in the AI-driven Replenishment Optimization process in
the correct order:
Answer: b) Analyze Demand Variability d) Consider Lead Times c) Determine Optimal Reorder
Points a) Calculate Optimal Reorder Quantities e) Minimize Excess Inventory
Question 4: Arrange the following components of AI-powered Supplier Management in the correct
order:
Answer: b) Historical Data Analysis a) Supplier Performance Prediction c) Optimal Sourcing
Decisions e) Supplier Relationship Optimization d) Supplier Collaboration
Question 5: Arrange the following steps of AI-driven Risk Management in the correct order:
Answer: c) Identification of Potential Risks e) Real-time Data Analysis b) Predictive Analytics a)
Early Detection of Disruptions d) Mitigation Strategies

Long answers
1. Explain Key challenges in Supply Chain Management.
Answer: Refer Section 5.1
2. Elaborate different ML Use Cases in Supply Chain.
Answer: Refer Section 5.2
3. How ML will work with Supply Chain? Explain with an example.
Answer: Refer Section 5.3
4. Write a note on inventory management using AI/ML.
Answer: Refer Section 5.1
5. Explain the role of AI/ML in Security of Supply Chain Management.
Answer: Refer Section 5.2
6. Write a note on warehouse management using AI/ML.
Answer: Refer Section 5.2
15
Short questions
1. How has AI and ML transformed inventory management and supply chain operations?
Answer: Refer Section 5.1
2. What specific AI techniques enhance demand forecasting accuracy?
Answer: Refer Section 5.1
3. How do ML models optimize supplier relationships in supply chain management?
Answer: Refer Section 5.2
4. How does AI proactively manage supply chain risks?
Answer: Refer Section 5.1
5. What are the key stages in implementing ML for supply chain excellence?
Answer: Refer Section 5.3
6. How have AI and ML improved customer satisfaction and revenue?
Answer: Refer Section 5.2

Suggested reading:
 Book: "Supply Chain Management with Artificial Intelligence" by Tsan-Ming Choi, T.C.
Edwin Cheng, and Zhi Li. This book explores how AI and ML techniques can be applied to
various aspects of supply chain management, including demand forecasting, inventory
optimization, risk management, and supplier collaboration.

 Book: "Machine Learning: A Probabilistic Perspective" by Kevin P. Murphy. While not

exclusively focused on supply chain, this book provides a comprehensive introduction to
machine learning techniques, including those applicable to demand forecasting and
decision-making in inventory management.

 Book: "Operations and Supply Chain Management: The Core" by F. Robert Jacobs and
Richard B. Chase. This textbook covers fundamental concepts in supply chain
management, including how technology, AI, and ML are transforming various aspects of
the supply chain.

 Article: "Using AI to Optimize Inventory" by Harpal Singh, Michael Hu, and Rajeev
Ranjan. Published in the Harvard Business Review, this article discusses how AI and ML
techniques can be leveraged to optimize inventory levels and enhance supply chain
efficiency.

 Article: "Supply Chain Optimization with Machine Learning" by Phil Gibbs and Chris
Cotteleer. This article, published by Deloitte, provides insights into how machine learning
16
 can be applied to supply chain optimization, including demand forecasting, inventory
management, and logistics.

 White Paper: "AI and Machine Learning in the Supply Chain" by DHL and IBM. This
white paper explores the potential impact of AI and ML on various aspects of supply chain
management, including demand forecasting, inventory optimization, and transportation.

 Research Paper: "Machine Learning Applications in Supply Chain Management: A

Comprehensive Overview" by R. Acharjee, A. Dwivedi, and V. Nagarajan. This research
paper provides a comprehensive overview of machine learning applications in supply chain
management, including case studies and examples.

 Research Paper: "Artificial Intelligence in the Supply Chain: A Synthesis of Applications,

Trends, Challenges, and Opportunities" by G. Shafiq, Z. Li, and S. R. Kannan. This
research paper presents an overview of AI applications in supply chain management and
discusses the challenges and opportunities associated with their implementation.

 https://www.n-ix.com/machine-learning-supply-chain-use-cases

17