International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395 -0056
Volume: 04 Issue: 03 | Mar -2017
p-ISSN: 2395-0072
www.irjet.net
Demand Value Identification Using Improved Vector Analysis Shivnarayan Rajput1, Prof. P M Chawan2 Department of Computer Engineering, VJTI, Mumbai, Maharashtra, India Professor, Department of Computer Engineering, VJTI, Mumbai, Maharashtra, India ---------------------------------------------------------------------***--------------------------------------------------------------------1
2
Abstract - Supply chain can be said as a set of distributed
provide a model with better explanation to present the supply chain demand.
entities composed of distributors, retailer’s manufacturers, suppliers, and costumers. Supply chain management (SCM) is the supervision of its three flows: the materials flow, the finances flow and the information flow. Indeed, this paper focuses on the information flow, more precisely on sharing information within a one echelon supply chain. Supply chain management (SCM) is an emerging field that has commanded attention from different communities. On the one hand, the optimization of supply chain which is an important issue, it requires a reliable future demand prediction. On the other hand, it has been shown that intelligent systems and machine learning techniques are useful for forecasting in several applied domains. In this paper, we used the Particle Swarm Optimization (PSO) algorithm to optimize the SVR parameters. Furthermore, we will use the Artificial Bee Colony (ABC) algorithm to optimize SVR parameters. Furthermore, we will find the time complexity of SVR- PSO and SVR-ABC for supply chain demand forecasting and compare these two algorithms. The goal of our work is to optimize both inventory and transportation costs by using the concept of SVR-ABC.
The two types of flows are: products flow (from supplierretailer to market) and information flow (from marketretailer to supplier).
Fig 1. Supply Chain Following are the advantages of Demand forecasting -
Key Words: Supply Vector Machine(SVM), Supply Vector Regression(SVR), Particle Swarm Optimization(PSO), Artificial Bee colony(ABC), Supply Chain Management.
1.INTRODUCTION
1.1 Objectives
Demand forecasts play an important role in supply chain management. Demand forecasting is predicting future demand for the product. In other words, it means the prediction of probable demand for a product or a service on the basis of the prevailing trends in the present and past events. The future demand for a certain product is the basis for the optimization of supply chain and of replenishment systems. The benefits of the demand forecasts can be grouped around two main concepts: firstly, the reduction storage costs by the optimization of the stock and secondly the optimization of operations with the development of optimal strategies for procurement.
A quick response of production systems to changes in consumer demand is not possible. Therefore, demand forecasting is necessary to estimate future consumer demand for a product or service. These demand data serve as the basis of capacity and facility planning and also selection of appropriate inventory levels, capital investments and departmental budgets, material and supplies acquisitions, marketing plans and human resources activities. The main objectives of any supply chain management(SCM) is to improve the overall organization performance and customer satisfaction by improving the product or service delivery to consumer. Also, other objective of any effective supply chain management (SCM) system is to satisfy the customer demand with very low or minimum costs. In our case, we will be focusing on optimizing inventory costs by using the information flow,
We present here demand forecasting approach with Support vector regression. Then, the supply chain will be proposed with a method to present the probabilistic demand. The recent machine learning technique, SVM which overcomes the drawbacks of neural networks, has been introduced to
© 2017, IRJET
|
Helps to Predict the Future Learn from The Past Reduce Inventory Costs Helps Prepare for a Drop-in Sales
Impact Factor value: 5.181
|
ISO 9001:2008 Certified Journal
|
Page 1648