Product Lifecycle Forecasting Using System's Indicators

Abstract

The concept of product lifecycle is one of the tools of strategic management and gives a company the guidelines for marketing their product. It is very important that companies know in which lifecycle stage their product is. When conceiving a product platform, companies rely on the researches of socioeconomic parameters. These parameters are called influence parameters, because by changing through time they influence the sales of the product and consequently the lifecycle curve, and require the company to change its business model, business strategy or their product. The changes of influence parameters reflect the changes of consumer needs, which is why in most cases the product needs to be adapted to the new parameters. In order for companies to know in which lifecycle stage the product is or will be, they often use forecasting methods. In this process, all the socio-economic parameters are projected that were valid in that specific period. The purpose of the article is to develop a model that takes into account the changing of influence parameters and gives reliable medium-term forecasts of the sales of a given product (attached is an example of a built-in oven lifecycle).

Fostering Alliances with Customers for the Sustainable Product Creation

“…In the last century they people were struggling with the problem of how to make things, while today we are thinking about how to make the product with a lowest possible cost, to sell it successfully, to maximize its profits and to satisfy the customer at the same time [1]. In particular, the latter is the starting point for a good reputation of the company.…”

“…If this is successful, the next step is production planning and the production itself (materials, parts, equipment are needed). The product continues its journey to the store, then into use, and finally to removal [1].…”

Forecasting emergency medicine reserve demand with a novel decomposition-ensemble methodology

“…Therefore, the original time series tends to comprise very complex components, which renders a big challenge for the forecasting task. Despite that it is proved that including the key factors into the model can improve the prediction results [ 40 , 41 ], it is impossible to identify and quantify all the factors, consequently some useful components cannot be captured by the traditional models and are ignored as noise, which lead to unsatisfactory performance of the traditional models.…”

“…The frequency decreases when we check the modes from IMF2 to the residual series. As shown by [ 40 , 41 ], data preprocessing plays a very important role in forecasting. For higher forecasting accuracy, it is necessary to appropriately preprocess the data before run the forecasting models, among which, matching the IMFs, individually or in combinations, with the suited models is a key task.…”

The Design of an Agent-Based System for Capital Markets

“…An agent can learn by experience (Rehar et al, 2017). Experience means the perception of the environment's evolution in the aftermath of the actions performed by the agent in various situations and of the interactions with other agents (Gil et al, 2012).…”