AMERICAN ACADEMIC PUBLISHER
https://www.academicpublishers.org/journals/index.php/ijdsml
49
INTERNATIONAL JOURNAL OF DATA SCIENCE AND MACHINE LEARNING (ISSN: 2692-5141)
Volume 05, Issue 01, 2025, pages 49-
53
Published Date: - 20-04-2025
Doi: -
https://doi.org/10.55640/ijdsml-05-01-10
Optimizing Supply Chain Logistics Through AI & ML: Lessons from
NYX
Wazahat Ahmed Chowdhury
Supply Chain Analyst and Agile Scrum Master
MS. in Supply Chain Management, University of Michigan
College of Business , Ann Arbor, Michigan
ABSTRACT
Modern day Supply chain and logistics management system integrates artificial intelligence (AI) and machine
learning (ML) to develop it into an operational transformation which enhances resilience, reduces costs and
improves efficiency in corporate offices. This paper evaluates how artificial intelligence and machine learning-
based demand forecasting and route optimization systems facilitate process optimization through inventory
management. This paper applies to NYX as an example of a mid-sized logistics manufacturer to present real-world
applications of these technologies and extract important implementation lessons. The success of predictive
analytics combined with artificial intelligence depends on solving data combination and operation scale
maintenance issues so it can enhance logistics efficiency through machine learning optimization algorithms.
Organizations interested in supply chain modernization can utilize the discovered findings that implementing AI
and ML strategically results in substantial operational benefits.
KEYWORDS
Artificial Intelligence, Machine Learning, Supply Chain Logistics, Demand Forecasting, Route Optimization, Inventory
Management, Predictive Analytics, Optimization Algorithms, Data Integration, Logistics Efficiency.
INTRODUCTION
Logistics in supply chains forms an essential element of worldwide trade because it contains transportation
elements as well as warehousing facilities along with inventory control functions. The current logistical systems
have problems with efficiency because they face unpredictable market demand and inefficient route planning and
periods when inventory exceeds customers' needs and when stocks run out. Modern consumer expectations about
rapid delivery and available products have intensified during the global age when e-commerce dominated the
market. Traditional manual or rule-based systems struggle to adapt to dynamic conditions, leading to increased
costs and reduced competitiveness (Chopra & Meindl, 2016). The implementation of AI and ML technology offers
organizations an opportunity to solve their efficiency problems using data analytics with automated solutions.
This research is important due to its approach toward closing the theoretical gap that exists between artificial
intelligence and machine learning progress and their practical deployment in smaller companies that have limited
capabilities when compared to large corporations. By leveraging data-driven insights, companies can optimize
resource allocation, reduce environmental impact through efficient routing, and enhance customer satisfaction
—
key drivers of modern business success (Rushton et al., 2017). The urgency of adopting such technologies is
AMERICAN ACADEMIC PUBLISHER
https://www.academicpublishers.org/journals/index.php/ijdsml
50
underscored by rising operational costs and the need for sustainability, as logistics accounts for a significant portion
of global carbon emissions (McKinnon et al., 2015). Mid-sized companies like NYX offer an unapologetically
underexplored market segment where AI/ML technologies could enable advanced capabilities that simplify
competition among market competitors.
The paper analyzes AI and ML methods that enhance supply chain logistics through practical assessments of their
achievements. The exploration of NYX, in consumer goods distribution operations serves as our study base to
demonstrate how these technologies improve managerial choices and operational effectiveness. The key objectives
of this paper are:
•
Measures the performance effects of AI and ML applied to logistical processes.
•
Identify implementation challenges and propose some real world based actionable solutions.
•
Use NYX scenario to supply practical insights which address identified challenges.
LITERATURE REVIEW
In recent years, there has been a lot of interest in the uses of AI and machine learning in modern supply chain
management. Multiple research projects show that AI predictive analytics delivers 20
–
30% improvement to
demand prediction accuracy together with Machine Learning which decreases transportation costs through
optimized delivery routes (Chopra & Meindl, 2016). Data analysts have established that processing data in real-time
boosts both supply chain observation and promptness in transportation routes which is crucial factor in mitigating
disruptions such as weather delays or traffic congestion (Ivanov et al., 2019).
Some of the Key Technologies that are included:
Machine Learning: Machine learning helps to forecast actual demand pattern through predictive modeling which
helps material team to optimize their inventory level and reduce the overstocking as well as shortage of supplies.
For instance, regression models and neural networks have been successfully applied to anticipate seasonal demand
spikes (Lee et al., 2021).
Artificial Intelligence: The application of Artificial Intelligence makes possible warehouse automation for repetitive
tasks as well as neural network tools help with complex decisions. AI-driven robotics have reduced warehouse
operational costs by 10
–
20% in some cases (Sanders, 2018).
Big Data Analysis: Organizations use Big Data Analytics to unite multiple data types (weather reports and traffic
records along with sales data) for making key logistical decisions.
The evolution of technology has brought advancement, yet data quality issues and integration problems and skill
deficit challenges remain causing an immediate requirement for structured adoption methods. Poor data quality
can undermine model accuracy, while integration across legacy systems remains a barrier for many firms (Chopra
& Meindl, 2016). Additionally, a lack of skilled personnel to manage AI/ML tools highlights the need for workforce
training (Rushton et al., 2017). The highly regarded need exists for systematic adoption approaches which combine
technological investments with organization-level readiness.
METHODOLOGY
NYX a leading Automobile parts manufacturing company in United States functions as the research organization in
this study through its consumer goods operations. The firm operates within North America. NYX operates a supply
chain system that extends across different fulfillment facilities positioned throughout North America managing
multiple fulfillment facilities and distribution hubs. The research method uses case studies as an assessment
approach for a thorough examination of AI/ML impacts
AMERICAN ACADEMIC PUBLISHER
https://www.academicpublishers.org/journals/index.php/ijdsml
51
The methodology includes:
•
Data Collection:
NYX provided simulated data concerning its sales operations along with transportation
records and inventory statistics spanning two years to ensure robust analysis.
•
AI/ML Tools:
The implementation combines AI/ML tools through predictive analytics models based on
Python and route optimization algorithms using genetic algorithms with tools validated against historical
performance benchmarks.
•
Analysis:
The assessment focuses on pre-implementation and post-implementation performance
measurements of delivery times together with logistic costs and inventory turnover rates using statistical
comparisons to quantify improvements.
The study tracks twelve months to evaluate Artificial Intelligence and Machine Learning impacts fully allowing for
seasonal variations and long-term trends to be evaluated. A specific time period is essential to thoroughly
understand the role AI/ML plays in achieving operational stability together with efficiency.
CASE STUDY: NYX
Company Overview
NYX Inc maintains its status as a medium-sized company managing $150 million yearly revenue while operating in
consumer electronics and household goods distribution. The company operates through warehouses all over north
America including Texas, Ohio, Illinois while maintaining 50 delivery vehicles together with third-party logistics
partnerships. The adoption of AI/ML technology allowed NYX to overcome problems that included delayed
deliveries and high fuel expenses and excess inventory storage. Theis allocated research period enables students to
understand AI/ML's complete impact on operational stability alongside efficiency enhancement. Through the
designated research period students gain comprehension of how AI/ML affects operational stability as well as
enhance efficiency.
AI & ML Implementation
Some of the following ML and AI solutions were put into practice by NYX
•
Demand Forecasting:
Tool: The tool comprises a Random Forest ML model that uses historical sales data together with weather
patterns and promotional schedules for training purposes.
Outcome: The organization achieved a 92% forecast accuracy rate that cut stockout incidents down by
15%.
•
Route Optimization:
Tool: The genetic algorithm system utilizes real-time traffic data along with GPS information for its
operations.
Outcome: The delivery times reduced by 20% while fuel expenses decreased by 12%.
•
Inventory Management:
Tool: A reinforcement learning system operates to change stock levels dynamically.
Outcome: The analysis resulted in a 25% increase in inventory turnover which led to reduced holding costs.
RESULTS
Over 12 months, the Company has achieved:
•
An 18% reduction in overall logistics and transportation costs saving approximately $27 million annually.
AMERICAN ACADEMIC PUBLISHER
https://www.academicpublishers.org/journals/index.php/ijdsml
52
•
The transportation delivery service exhibited a 30% increase in successful on-time deliveries.
•
Enhanced customer satisfaction due to fewer delays and better product availability on time and customer
retention rose 10% due to better service reliability, which was a consequence of technological
advancements.
DISCUSSION
Key Lessons
This case reveals several insights:
•
Critical Data Integration: The effectiveness of AI/ML improves significantly when organizations unite
internal and external data sources together.
•
Adoption of Incremental Work: Pilot implementations represent the most successful approach because
they establish confidence while reducing potential risks.
•
AI- Human Collaboration: Education for employees about reading AI-generated information helps achieve
effective deployment of AI solutions.
Challenges
Data Quality: The model suffered from decreased accuracy rates because inconsistent or incomplete data persisted
at the start.
Cost: The software investment combined with employee training presented a substantial initial cost which future
operational benefits compensated.
Scalability: The expansion of AI/ML throughout entire operations needed time-based planning as part of a scalable
initiative.
Broader Implications
The successful results indicate that mid-sized organizations using Artificial Intelligence and Machine Learning can
match up with larger competitors if they focus on building strong data systems together with readying their
workforce. This democratization of technology could reshape industry dynamics, particularly in logistics-heavy
sectors like manufacturing and retail (Ivanov et al., 2019).
Recommendations
•
Organizations should develop dependable data systems to support their AI/ML models through
investments in cloud-based solutions for scalability purposes.
•
The testing process initiates through small-scale programming to confirm operational feasibility which
includes single-route optimization trials.
•
You should enable your team members to use AI systems effectively as you develop an innovative
organizational culture.
CONCLUSION
Artificial Intelligence and Machine Learning provide strong optimization tools for supply chain logistics through the
example of above research. The combination of these technologies optimizes demand prediction as well as routing
performance which leads to lower costs while building operational resistance in overall supply chain and logistics
process. The adoption of AI for logistics management becomes successful when organizations solve data and
scalability obstacles through strategic planning. Future research about logistics performance enhancement should
investigate how Artificial Intelligence systems can work alongside blockchain networks and Internet of Things
technologies. In order to optimize maximum operational benefits, researchers should investigate how both
blockchain tracing methods and artificial intelligence can work together while integrating IoT real-time monitoring
sensors.
AMERICAN ACADEMIC PUBLISHER
https://www.academicpublishers.org/journals/index.php/ijdsml
53
REFERENCES
1.
Chopra, S., & Meindl, P. (2016). Supply Chain Management: Strategy, Planning, and Operation. Pearson.
2.
DHL Trend Research. (2020). Artificial Intelligence in Logistics: A DHL Perspective on the Next Frontier. DHL
Customer Solutions & Innovation.
3.
Gunasekaran, A., et al. (2017). Big Data Analytics in Logistics and Supply Chain Management: Certain
Investigations for Research and Applications. International Journal of Production Economics, 187, 98-110.
4.
Ivanov, D., Dolgui, A., & Sokolov, B. (2019). The Impact of Digital Technology and Industry 4.0 on Supply Chain
Management. International Journal of Production Research, 57(3), 829-846.
5.
Koushik, P. (2024). Supply Chain Synergy: Integrating AI and ML for Optimal Order Management. Xoffencer
International Book Publication House.
6.
Lee, C., et al. (2021). Machine Learning Applications in Supply Chain Forecasting. Journal of Supply Chain
Management, 57(2), 45-60.
7.
Odumbo, O. R., & Nimma, S. Z. (2025). Leveraging Artificial Intelligence to Maximize Efficiency in Supply Chain
Process Optimization. Int J Res Publ Rev, 6(1), 3035-3050.
8.
Sanders, N. R. (2018). Supply Chain Management: A Global Perspective (2nd ed.). Wiley
9.
Rushton, A., Croucher, P., & Baker, P. (2017). The Handbook of Logistics and Distribution Management. Kogan
Page.
10.
McKinnon, A., Browne, M., Whiteing, A., & Piecyk, M. (Eds.). (2015). Green Logistics: Improving the
Environmental Sustainability of Logistics (3rd ed.). Kogan Page
