image
image
user-login
Patent search/

INVENTORY MANAGEMENT EVALUATION AND PLANNING MACHINE LEARNING

search

Patent Search in India

  • tick

    Extensive patent search conducted by a registered patent agent

  • tick

    Patent search done by experts in under 48hrs

₹999

₹399

Talk to expert

INVENTORY MANAGEMENT EVALUATION AND PLANNING MACHINE LEARNING

ORDINARY APPLICATION

Published

date

Filed on 14 November 2024

Abstract

INVENTORY MANAGEMENT EVALUATION AND PLANNING MACHINE LEARNING Abstract : In the contemporary business landscape, effective inventory management is pivotal for operational efficiency and cost control. This research delves into the utilization of Machine Learning (ML) techniques to enhance inventory evaluation and planning processes. We start by outlining the traditional challenges in inventory management, including demand forecasting, stock level optimization, and supply chain complexities. The paper then introduces ML algorithms as innovative solutions to these challenges. We discuss various ML models, such as time series analysis, regression models, and neural networks, highlighting their respective strengths in predicting product demand, identifying patterns in sales data, and optimizing stock levels. A comparative analysis of these models is presented, based on their accuracy, scalability, and implementation complexity. A significant portion of the study is dedicated to case studies where ML has been successfully implemented in inventory management, providing empirical evidence of its efficacy. These case studies span different industries, showcasing the versatility of ML applications. Furthermore, we address the integration of ML models with existing Inventory Management Systems (IMS), discussing the technical and organizational considerations necessary for successful implementation. The paper concludes with future research directions, emphasizing the need for adaptive models that can respond to market volatility and the integration of Big Data analytics for more comprehensive inventory insights. This research contributes to the field by providing a detailed overview of how ML can revolutionize inventory management, offering practical insights for businesses aiming to enhance their inventory systems through technological innovation.

Patent Information

Application ID202441088153
Date of Application14/11/2024
Publication Number47/2024

Inventors

NameAddressCountryNationality
Dr. G. MahendrakumarAssistant Professor, Department of Mathematics, Erode Sengunthar Engineering College, Perundurai, Erode, Pin: 638057, Tamil Nadu, India.IndiaIndia
Mrs. K. BrindhaAssistant Professor, Department of Data Science, Sri Krishna Adithya College of Arts and Science, Coimbatore, Pin: 641042, Tamilnadu, India.IndiaIndia
Dr. R. S. Padma PriyaAssistant Professor, Vignan's Foundation for Science Technology and Research, Guntur, Pin: 522213, Andhra Pradesh, India.IndiaIndia
Mrs. P. MathiazhaganAssistant professor, Department of Computer Applications, Dr SNS Rajalakshmi College of Arts and Science (Autonomous), Coimbatore, Pin: 641049, Tamilnadu, India.IndiaIndia
Mrs. K Pandi MeenaAssistant Professor, Department of BCA, SRMIST, FSH, Ramapuram, Chennai, Pin: 600089, Tamilnadu, India.IndiaIndia
Dr. Chandrakala V GAssociate Professor, Department of MBA, Dr.HN National College of Engineering, 36 th B cross,7 th block, Jayanagar, Bengaluru Pin: 560070, Karnataka, India.IndiaIndia
Dr. R. RamyadeviAssistant professor, Department of Computer Science and Applications, SRM Institute of Science and Technology, Bharathi salai, Ramapuram, Chennai, Pin: 600089, Tamilnadu, India.IndiaIndia
Ms. K. SangeethaAssistant Professor, Department of Computer, Science (Graphics & Creative Design), Dr.SNS Rajalakshmi College of Arts and Science, Coimbatore, Pin: 641049, Tamilnadu, India.IndiaIndia
Mr. M. PraveenkumarAssistant professor, Department of Cyber Security, Dr.SNS Rajalakshmi College of Arts and Science, Coimbatore, Pin: 641049, Tamilnadu, India.IndiaIndia
Mrs. G. K. KarthigaAssistant Professor, Department of Cyber Security, Dr.SNS Rajalakshmi College of Arts and Science, Coimbatore, Pin: 641049, Tamilnadu, India.IndiaIndia

Applicants

NameAddressCountryNationality
Dr. G. MahendrakumarAssistant Professor, Department of Mathematics, Erode Sengunthar Engineering College, Perundurai, Erode, Pin: 638057, Tamil Nadu, India.IndiaIndia
Mrs. K. BrindhaAssistant Professor, Department of Data Science, Sri Krishna Adithya College of Arts and Science, Coimbatore, Pin: 641042, Tamilnadu, India.IndiaIndia
Dr. R. S. Padma PriyaAssistant Professor, Vignan's Foundation for Science Technology and Research, Guntur, Pin: 522213, Andhra Pradesh, India.IndiaIndia
Mrs. P. MathiazhaganAssistant professor, Department of Computer Applications, Dr SNS Rajalakshmi College of Arts and Science (Autonomous), Coimbatore, Pin: 641049, Tamilnadu, India.IndiaIndia
Mrs. K Pandi MeenaAssistant Professor, Department of BCA, SRMIST, FSH, Ramapuram, Chennai, Pin: 600089, Tamilnadu, India.IndiaIndia
Dr. Chandrakala V GAssociate Professor, Department of MBA, Dr.HN National College of Engineering, 36 th B cross,7 th block, Jayanagar, Bengaluru Pin: 560070, Karnataka, India.IndiaIndia
Dr. R. RamyadeviAssistant professor, Department of Computer Science and Applications, SRM Institute of Science and Technology, Bharathi salai, Ramapuram, Chennai, Pin: 600089, Tamilnadu, India.IndiaIndia
Ms. K. SangeethaAssistant Professor, Department of Computer, Science (Graphics & Creative Design), Dr.SNS Rajalakshmi College of Arts and Science, Coimbatore, Pin: 641049, Tamilnadu, India.IndiaIndia
Mr. M. PraveenkumarAssistant professor, Department of Cyber Security, Dr.SNS Rajalakshmi College of Arts and Science, Coimbatore, Pin: 641049, Tamilnadu, India.IndiaIndia
Mrs. G. K. KarthigaAssistant Professor, Department of Cyber Security, Dr.SNS Rajalakshmi College of Arts and Science, Coimbatore, Pin: 641049, Tamilnadu, India.IndiaIndia

Specification

Description:Objective :
Artificial intelligence and big data has disrupted the industry, as the barriers of its implementation (cost, computing power, open-source platforms, etc) disappear. In This context, machine learning is applied on the design and development of predictive models which assess all areas of management, providing essential insights for companies to understand and react to changes in its operation. A subject profoundly discussed in supply chain management is the inventory planning, which is an essential activity for any enterprise which tries to determine the decision about when to order and how much should order, considering different mechanisms of control. Most of the approaches proposed so far formulate the problem as a multi-objective optimization one: ordering and storage costs must be held to a minimum, while service level leverage is as high as possible.

A different approach for managing the inventory more efficiently - and complementary to the models developed in literature - is to identify the materials at risk of backorder before the event occurs, conferring the business a suitable time to react. A complication uprises in this particular kind of supervised learning application, since in regular inventory system the number of items which goes on backorder (positive The current research is supported by Brazilian Federal Agency for Post-graduate Education (CAPES).or majority class) is utterly inferior to the amount of active items (negative or minority class).

This case is known as the class imbalance problem and it is common in many other real problems from telecommunications, web, finance-world, ecology, biology, medicine, among others, and requires appropriate techniques for handling the construction of the prediction model desired.This paper proposes the application of a supervised learning model for backorder prediction in inventory control, based on the combination of sampling methods and ensemble of learning classifiers, and present results obtained in a real case study.

The Inventory Management System in hospital wards is a process in which, it has a real-time status of all the available beds and the bed occupied, to plan for the efficient use of beds, medicines and medical equipment. It helps the hospital staff and management by reducing the time of counting and recording the availability of beds. Healthcare inventory management is incredibly important in Hospital wards. Inventory management systems can help hospitals and other medical organizations streamline their processes to save time while providing quality care to patients. After an accident, inconvenient waiting hours in hospital waiting halls due to improper operational capacity planning and control over managing, allotting, and maintaining beds may turn frustrating when emergency care is required.


The lack of real-time data analysis provides a disadvantage resulting in patient overcrowding and malefactions in inpatient bed management services during emergencies. Monitoring and managing inpatient-outpatient capacity & patient inflows can be challenging tasks during emergencies. Unplanned inventory, the inability to beds, and other scarce resources may lead to poor operations, and that affects the hospital's goodwill.

The contextual backdrop of this research is Bangladesh, a country where a substantial portion of the population is engaged in entrepreneurial pursuits. Consequently, a plethora of shops, varied retail outlets, and super shops dot different regions, each stocked with diverse models and products to meet consumer demands. The myriad attributes influencing demand prediction include data availability, timing of forecasting, historical records, past demand patterns, location, and special occasions. The interplay of these factors underscores the complexity of forecasting in a multifaceted retail landscape.

Effective demand prediction methods not only contribute to minimizing inventory costs but also play a pivotal role in ensuring product availability. The primary objective is to streamline inventory costs, making optimal demand prediction indispensable. Recognizing this, the research emphasizes the critical role of accurate demand forecasting in establishing an efficient supply chain.
Employing advanced machine learning techniques, the study focuses on different algorithms to predict future customer demands for specific products. In the competitive retail landscape, the consequences of stockouts are profound, potentially resulting in lost sales and dissatisfied customers. The challenge lies in accurately predicting customer preferences and demands, especially within the middle and low-level consumer segments where confidentiality is harder to maintain.

This research delves into the impact of accurate prediction on retail sales, acknowledging the increasing competition among retailers and the importance of understanding customer behavior across various market segments. Considering market dynamics and financial constraints within the retail sector, accurate predictions become pivotal. The adoption of technology, modern tools, and innovative predictive methods is becoming imperative for retailers aiming to forecast customer demands effectively.
Description:
Random Forest Algorithm:
Random Forest is a popular machine learning algorithm that belongs to the supervised learning technique. It can be used for both Classification and Regression problems in ML. It is based on the concept of ensemble learning, which is a process of combining multiple classifiers to solve a complex problem and to improve the performance of the model.
As the name suggests, "Random Forest is a classifier that contains a number of decision trees on various subsets of the given dataset and takes the average to improve the predictive accuracy of that dataset." Instead of relying on one decision tree, the random forest takes the prediction from each tree and based on the majority votes of predictions, and it predicts the final output.

Assumptions for Random Forest:
Since the random forest combines multiple trees to predict the class of the dataset, it is possible that some decision trees may predict the correct output, while others may not. But together, all the trees predict the correct output. Therefore, below are two assumptions for a better Random forest classifier:

● There should be some actual values in the feature variable of the dataset so that the classifier can predict accurate results rather than a guessed result.
● The predictions from each tree must have very low correlations.

Why use Random Forest:
Below are some points that explain why we should use the Random Forest algorithm:

● It takes less training time as compared to other algorithms.
● It predicts output with high accuracy, even for the large dataset it runs efficiently.
● It can also maintain accuracy when a large proportion of data is missing.

How does the Random Forest algorithm work:
Random Forest works in two-phase first is to create the random forest by combining N decision trees, and second is to make predictions for each tree created in the first phase.
The Working process can be explained in the below steps and diagram:
Step-1: Select random K data points from the training set.
Step-2: Build the decision trees associated with the selected data points (Subsets).
Step-3: Choose the number N for decision trees that you want to build.
Step-4: Repeat Step 1 & 2.
Step-5: For new data points, find the predictions of each decision tree, and assign the new data points to the category that wins the majority votes.
The working of the algorithm can be better understood by the below example:
Example: Suppose there is a dataset that contains multiple fruit images. So, this dataset is given to the Random forest classifier. The dataset is divided into subsets and given to each decision tree. During the training phase, each decision tree produces a prediction result, and when a new data point occurs, then based on the majority of results, the Random Forest classifier predicts the final decision. Applications of Random Forest:
There are mainly four sectors where Random forest mostly used:

1. Banking: Banking sector mostly uses this algorithm for the identification of loan risk.
2. Medicine: With the help of this algorithm, disease trends and risks of the disease can be identified.
3. Land Use: We can identify the areas of similar land use by this algorithm.
4. Marketing: Marketing trends can be identified using this algorithm.

2.1.1 Advantages of the proposed system

Handling Non-Linear Data: Random Forest is adept at handling non-linear relationships in data, which is often the case in inventory management where complex patterns and relationships might exist.

Feature Importance: One of the most beneficial aspects of Random Forest is its ability to rank the importance of different features for prediction. This can provide valuable insights into which factors most significantly affect inventory levels, demand forecasting, etc.

Robustness to Overfitting: Due to the nature of building multiple trees and using the average to make decisions, Random Forest is generally more robust to overfitting compared to many other algorithms, especially when dealing with large datasets.

Handling Missing Values: Random Forest can handle missing values in the data. While it's still advisable to properly preprocess the data, this feature can be useful in real-world scenarios where data might not always be complete.

Flexibility with Different Types of Data: It can handle both categorical and numerical data without the need for extensive preprocessing like normalization or scaling, which is often required in other algorithms.

The system design for Inventory Management
(Evaluation and Planningusing Machine Learning) with Random Forest over XGBoost Algorithm involves several key components to effectively optimize inventory levels and streamline supply chain operations. Firstly, the system integrates data collection mechanisms to gather historical sales data, inventory levels, and other relevant variables such as seasonality, promotions, and external factors like economic conditions or supplier lead times. This data is then preprocessed and cleaned to ensure accuracy and reliability, preparing it for input into the machine learning models.

Secondly, the system incorporates two machine learning algorithms, Random Forest and XGBoost, to perform inventory evaluation and planning tasks. Random Forest, known for its ensemble learning approach and ability to handle high-dimensional data, is utilized for inventory evaluation, where it predicts future demand based on historical sales data and other relevant features. On the other hand, XGBoost, a gradient boosting algorithm, is employed for inventory planning, leveraging its optimization capabilities to determine the optimal inventory levels that balance cost and service level objectives. These models are trained on historical data and continuously updated with new information to adapt to changing market conditions and demand patterns. Finally, the system provides actionable insights and recommendations to inventory managers, enabling them to make data-driven decisions to optimize inventory levels, minimize stockouts and excess inventory, and improve overall supply chain efficiency.

Through the integration of machine learning algorithms and robust data management processes, the system enhances inventory management practices and drives operational excellence in organizations.
In the database design for Inventory Management with Random Forest over XGBoost Algorithm, the primary focus is on structuring the database to efficiently store and manage the data required for machine learning model training and prediction. The database typically consists of multiple tables representing different entities and relationships involved in inventory management, such as products, sales transactions, inventory levels, suppliers, and external factors affecting demand.

One of the key tables in the database is the "Sales" table, which stores historical sales data including information about the products sold, quantities, prices, and timestamps. This data serves as the foundation for training the machine learning models, allowing them to learn patterns and trends in demand over time. Additionally, there may be tables to store inventory levels, procurement data, supplier information, and external factors such as economic indicators or weather conditions. These tables are designed to efficiently handle large volumes of data and support complex queries required for model training and prediction. Overall, the database design aims to provide a robust and scalable infrastructure for managing inventory data and supporting machine learning-based inventory management processes.

, Claims:CLAIMS:

1. This paper addresses the intricate relationship between customers and retailers, shedding light on the nature of the retail shop section and the dynamics at play in this sector.
2. The forecasting algorithms and methodologies discussed herein leverage data from the previous month, highlighting the importance of historical trends in predicting future product demands.
3. The research employs data from three distinct shops, utilizing machine learning and data mining to introduce novel models applicable to time series forecasting.
4. In an era where autonomous decision making systems are gaining prominence, the study employs Random Forest, XGBooster, and Decision Tree Classifier for effective data classification and decision-making.
5. This study endeavors to determine the optimal technique for demand forecasting by examining various features.
6. The literature review section offers insights into previous forecasting methodologies, setting the stage for the methodology section, where the research approach is delineated.
7. The ensuing performance measurement section elucidates the calculation process, and the performance analysis section scrutinizes the results, ultimately identifying the most effective forecasting method.

Documents

NameDate
202441088153-COMPLETE SPECIFICATION [14-11-2024(online)].pdf14/11/2024
202441088153-DECLARATION OF INVENTORSHIP (FORM 5) [14-11-2024(online)].pdf14/11/2024
202441088153-FORM 1 [14-11-2024(online)].pdf14/11/2024
202441088153-FORM-9 [14-11-2024(online)].pdf14/11/2024
202441088153-POWER OF AUTHORITY [14-11-2024(online)].pdf14/11/2024
202441088153-REQUEST FOR EARLY PUBLICATION(FORM-9) [14-11-2024(online)].pdf14/11/2024

footer-service

By continuing past this page, you agree to our Terms of Service,Cookie PolicyPrivacy Policy  and  Refund Policy  © - Uber9 Business Process Services Private Limited. All rights reserved.

Uber9 Business Process Services Private Limited, CIN - U74900TN2014PTC098414, GSTIN - 33AABCU7650C1ZM, Registered Office Address - F-97, Newry Shreya Apartments Anna Nagar East, Chennai, Tamil Nadu 600102, India.

Please note that we are a facilitating platform enabling access to reliable professionals. We are not a law firm and do not provide legal services ourselves. The information on this website is for the purpose of knowledge only and should not be relied upon as legal advice or opinion.