INTERNATIONAL JOURNAL OF RESEARCH AND SCIENTIFIC INNOVATION (IJRSI)

ISSN No. 2321-2705 | DOI: 10.51244/IJRSI |Volume XII Issue IX September 2025

Page 3991

www.rsisinternational.org

The Role of Artificial Intelligence in Optimising Retail Inventory

Management

Sangeeta Jha

Satyadev Singh

Asst. Professor, Pacific Institute of Business Studies

Scholar, Business Administration, Pacific Academy of Higher Education and Research University,

Udaipur.

DOI:

https://doi.org/10.51244/IJRSI.2025.120800357

Received: 14 September 2025; Accepted 21 September 2025; Published: 14 October 2025

ABSTRACT

This review paper examines how Artificial Intelligence (AI) is transforming retail inventory management with

predictive analytics, machine learning algorithms, and automation. Drawing on the results of four articles, the

review examines AI-facilitated enhancements in demand forecasting, inventory optimization, supply chain

integration, and reordering automation. The study also examines challenges and strategic implications of

leveraging AI in the retail industry. The study establishes the premise that not only does AI enhance forecasting

accuracy and response time, but it also supports lean inventory practices, scalability, and real-time

responsiveness. With the help of AI, retail firms try to realign their inventory to achieve its full potential.

Keywords: Artificial Intelligence, Inventory Management, Retail, Demand Forecasting, Machine Learning,

Automation, Supply Chain.

INTRODUCTION

Inventory management is one of the key factor that exerts a great influence on operational efficiency and

profitability. Inventory management is really all about aligning customers' demand and supply costs at the lowest

possible expense and not through stockouts or overstocks. Statistical techniques and tools have been the answer

to this in the past. These do not do justice, however, to the dynamics of the contemporary retail market, including

rapidly changing consumers' behaviour, globalization, e-business growth, and supply chain risks.

With the current pace of the world, Artificial Intelligence (AI) has been a game-changer. AI refers to the ability

of machines to mimic human intelligence—learn, predict, and even make decisions themselves. In inventory

management, the application of AI is huge: from real-time forecasting and dynamic pricing to automated buying

and predictive maintenance of supply infrastructure. AI can assist businesses in freeing themselves from reactive

inventory procedures and moving towards proactive, data-driven decision-making procedures.

Ünal et al. (2023) note that deep learning, machine learning, and reinforcement learning, all branches of AI, are

the driving force behind the inventory management revolution. These technologies allow the retailers to handle

vast amounts of data, learn from fresh data, and control their inventory with such accuracy and speed as is

impossible by traditional means. For instance, AI not only can see past sales but also external influences like

weather, social media, and financial projections to compute demand.

Second, AI plays a key role in coordinating different parts of supply chains. M.K. Islam et.al. (2024) illustrate

in their cross-country study how AI implementation promotes higher transparency within supply networks to

enable coordination among retailers, warehouses, and suppliers. This leads to a more robust and agile study that

is able to handle disruptions and maintain service levels.

AI helps in achieving operational efficiency which ultimately results in customer satisfaction. AI-based

inventory systems provide the needed products at the correct time, which minimizes lost sales and improve the

overall shopping experience in the store. Oladele (2025) mentions Walmart and Amazon, big-box stores,

employing AI not only to forecast future demand but also to personalize product availability and to automate

INTERNATIONAL JOURNAL OF RESEARCH AND SCIENTIFIC INNOVATION (IJRSI)

ISSN No. 2321-2705 | DOI: 10.51244/IJRSI |Volume XII Issue IX September 2025

Page 3992

www.rsisinternational.org

restocking—practices that equate inventory with actual customer demand.

AI solutions are also extremely scalable and adaptable to implement in businesses of varying sizes. From small

shops with AI-based inventory solutions to multinationals with fully automated supply chains from end to end,

the technology can be implemented in varying intensities and configurations. Successful AI implementation is

less a question of technical readiness than one of cultural change, for example, upskilling staff and going digital.

This review paper takes evidence from four novel studies to create an integrative summary of how AI is

optimizing retail inventory management. It categorizes AI applications into demand forecasting, inventory

optimization, supply chain integration, and automation—and employs empirical studies, case studies, and

literature reviews to demonstrate the revolutionary nature of AI. It also discusses AI adoption issues and offers

future research and field implementation directions.

LITERATURE REVIEW

Veluru (2022) examined the sophisticated AI algorithms which includes gradient boosting regressors and LSTM

neural networks. It can enhance demand forecasting. The research explained that these models, through the

examination of past sales, seasonality, promotions, and other variables, are more accurate than conventional

statistical techniques. A correct forecasting helps companies to adopt just-in-time inventory systems which

lowers holding costs and reducing wastage.

In their 2023 study, Ünal et al. investigated the application of reinforcement learning and deep learning to

inventory management. Their research shown that these AI systems are able to use real-time supply and sales

data to determine the appropriate inventory levels and reorder points. Agility is improved by machine learning-

based solutions. It helps businesses in minimizing the shortage of stock. It also prevents overstocking and

responds quickly to changes in demand.

Al Bashar et al. (2024) argued that AI adoption improves the overall efficiency of the supply chain. Improved

visibility, proper maintenance, sensor-enabled monitoring etc. allow AI to plan logistics more effectively and

solve the problems in advance. Those firms which applied AI to their supply chains witnessed increased

responsiveness. It also helps in reducing interruptions in supply and thus helps in an improved coordination

between retailers, distributors, and suppliers.

Oladele (2025) investigated stock management automation using AI. The study confirmed that AI facilitates

forecast-based decision-making, stocking automation, and real-time monitoring. Automation increases

operational efficiency and reduces the chance of stockouts and overstocking. According to Oladele, AI-based

stock systems allow companies to grow effectively with little manual involvement while maintaining ideal stock

levels.

AI in Retail Inventory Management

Demand Forecasting: By examining previous purchase and sales, AI helps in forecasting future purchase. It

helps in minimising overstocking and understocking of goods.

Intelligent inventory choices: AI acts as an effective store manager. It monitors sales and supply data which

helps in calculating optimum stock.

Integration of supply chain: Hooking Everything Together Rather than separate components of the business

operating independently, AI facilitates suppliers, warehouses, and stores to operate like a single unit. It is similar

to everyone being in the same group message, sharing information immediately.

Operating on Autopilot: The most recent innovation is stores that function much like they're automated. AI

reorders products, monitors everything in real-time, and makes choices without human intervention necessary

for every little detail.

Computer vision: AI-powered cameras and drones can easily detect shelves to estimate inventory, recognize

INTERNATIONAL JOURNAL OF RESEARCH AND SCIENTIFIC INNOVATION (IJRSI)

ISSN No. 2321-2705 | DOI: 10.51244/IJRSI |Volume XII Issue IX September 2025

Page 3993

www.rsisinternational.org

items, detect damage, and monitor for misplaced items. Thus, AI helps in improving accuracy and reducing

manual effort. Reduction in manual effort saves time and energy which ultimately increases efficiency.

TECHNIQUES

Using a qualitative synthesis methodology, this review compares four peer-reviewed journals selected based on

method quality, proximal publication (2022–2025), and relevance. Data on AI applications in inventory

management, broken down by function (forecasting, optimization, automation, and integration), was obtained

by scanning the journals. To provide a fair viewpoint, data from case studies, bibliometric reviews, and

experiments were combined.

FINDINGS

Efficiency and Precision

According to studies, AI improves forecasting accuracy and operational effectiveness. For example, forecasting

accuracy rose by up to 30% when using predictive models (Veluru, 2022). This facilitates prompt decision-

making and more effective inventory management which ultimately increases profit.

Reduction of expenses and waste

AI systems improve lean inventory management by forecasting exact reorder quantities, reducing holding

expenses, and reducing spoilage (Ünal et al., 2023). Without sacrificing availability, the merchants avoided

unnecessary inventory to avoid overstocking.

Scalability and Integration

AI programs can be integrated with existing legacy ERP and SCM systems and upgraded in a modular fashion

rather than being replaced (Al Bashar et al., 2024). These are thus within the reach of mid-sized businesses and

not just technology behemoths.

Real-Time Decision-Making

AI facilitates real-time decision-making through real-time data streams and machine learning feedback loops

(Oladele, 2025). Dynamic responsiveness of this type is essential for retailers operating in volatile or highly

competitive markets.

INTERNATIONAL JOURNAL OF RESEARCH AND SCIENTIFIC INNOVATION (IJRSI)

ISSN No. 2321-2705 | DOI: 10.51244/IJRSI |Volume XII Issue IX September 2025

Page 3994

www.rsisinternational.org

CHALLENGES

Despite the potential, AI deployment is hampered by numerous challenges. Data availability and quality are

central challenges since the models require enormous amounts of clean data to learn. Al Bashar et al. (2024) and

Ünal et al. (2023) also claim that employee resistance and compatibility with current systems are additional

challenges. Ethical concerns of data privacy and AI bias need to be addressed by open algorithms and quality

data governance legislation.

CONCLUSION

AI's ability to facilitate data-driven, responsive, and efficient business processes has helped to a great extent in

retail inventory management. Technology plays a huge role in everything from automated reordering to real-

time inventory tracking to demand forecasting. To make it useful, however, human, data, and integration issues

must be resolved. Retail businesses will use AI software more if it is easy to use and intuitive. Future studies

must examine ethical concerns, industry-specific flexibility based on various retail approaches, and hybrid AI-

human models.

REFERENCES

1. Oladele, O. K. (2025). AI in Retail: Personalized Shopping Experiences, Inventory Management, and

Supply Chain Optimization.

2. Sekhar, C. (2022). Optimizing retail inventory management with ai: A predictive approach to demand

forecasting, stock optimization, and automated reordering. European Journal of Advances in Engineering

and Technology, 9(11), 89-94.

3. Islam, M. K., Ahmed, H., Al Bashar, M., & Taher, M. A. (2024). Role of artificial intelligence and

machine learning in optimizing inventory management across global industrial manufacturing & supply

chain: A multi-country review. International Journal of Management Information Systems and Data

Science, 1(2), 1-14.

4. Albayrak Ünal, Ö., Erkayman, B., & Usanmaz, B. (2023). Applications of artificial intelligence in

inventory management: A systematic review of the literature. Archives of computational methods in

engineering, 30(4), 2605-2625.

5. Mehta, A. Tax Revenue Composition: A Relative Assessment. Ahmed, Z. K., & Mehta, B. (2023). Role

of Reviews in Online Purchasing of Home Furnishing Items. Pacific Business Review

International, 16(4).

6. Choudhary, P. D., & Madhwani, R. (2013). AN ANALYTICAL STUDY OF IMPACT OF RECESSION

ON TOURISM & HOSPITALITY INDUSTRY. International Journal of Psychosocial

Rehabilitation, 17(2).

7. Chaplot, D. (2018). An impact of strategic management on the performance of organization: An

empirical investigation on selected organization of Rajasthan. International Journal of Research and

Analytical Reviews, 5(3), 1537-1543.

8. Ahmed, Z. K., & Mehta, B. (2023). Role of Reviews in Online Purchasing of Home Furnishing

Items. Pacific Business Review International, 16(4).

9. Mehta, A., & Hiran, D. (2023). Methods for Managing Change in Medium Size Business Organizations

of Small Cities. ASM Group of Institutes, Pune, India, 6.

10. Dave, K. K., & Paliwal, R. (2016). A study on consumer perception on malted health food drinks in

Udaipur city. International Journal of Management and Corporate Affairs (IJARS), 2(5), 1-27.

11. Sharma, R., Dadhich, M., & Chauhan, K. (2022). The Impact Assessment of Pandemic on Financial

Indicators of Selected BSE Listed Companies: A Comprehensive View. Int. Res. J. Eng. Technol., 9(2),

483-494.

12. Chaplot, D. (2017). Job satisfaction is step towards success:-a study of max life insurance. An

international Peer Reviewed & Referred Scholarly Research Journal for interdisciplinary studies, 5616-

5630.

13. Jha S., Khandelwal P. (2025).

A Study of Green Accounting Practices followed by Indian Companies

with reference to Global Reporting Initiative Standards, International Journal of Research and Analytical

Reviews,12(1), 412-417.