A survey on retail sales forecasting and prediction in fashion markets

Beheshti-Kashi, Samaneh; Karimi, Hamid Reza; Thoben, Klaus‐Dieter; Lütjen, Michael; Teucke, Michael

doi:10.1080/21642583.2014.999389

Cited by 76 publications

(31 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Likewise—in an industry like retail—ML can play a strategic role in sales forecasting (Beheshti-Kashi et al 2015; Kaneko and Yada 2016), new store placement (Karamshuk et al 2013), and in fraud detection (Trinh et al 2011). In the latter, ML is used in collecting data like in the process described by Dietterich in the environmental sensor example, by converting signals into data.…”

Section: Discussionmentioning

confidence: 99%

The Potential Role of AI in Anticipating Futures from a Design Process Perspective: From the Reflexive Description of “Design” to a Discussion of Influences by the Inclusion of AI in the Futures Research Process

Bevolo

Amati²

2020

World Futures Review

View full text Add to dashboard Cite

The key question behind this article is, How is AI impacting futures research, with particular focus on foresight and design futures? To address such question, this article reports on selected epistemological and methodological traits of design futures research, on the nature of Artificial Intelligence (AI), and the potential impact of AI on the design futures domain, offering a conceptual model as theoretical junction between the domains of foresight and design. Key topics and themes addressed were selectively focused on foresight, design, design futures, weak signals, and their role in relationship with visioning and the image, AI, and a multidisciplinary discussion of how these fields relate to each other. This article is based on desk research and dialogue among the two authors, both profiled professional experts in their respective fields of design futures and AI, with a track of experience both in academic and applied research. Therefore, sources include a rich texture of bibliographic information, combined with selected input from ongoing research activities on AI and related trends, as performed in the professional field.

show abstract

Section: Discussionmentioning

confidence: 99%

The Potential Role of AI in Anticipating Futures from a Design Process Perspective: From the Reflexive Description of “Design” to a Discussion of Influences by the Inclusion of AI in the Futures Research Process

Bevolo

Amati²

2020

World Futures Review

View full text Add to dashboard Cite

show abstract

“…They developed a two-stage sales forecasting system and showed the real benefits of advanced forecasting techniques for fast fashion retailing. For an overview of sales forecasting literature related to retail and fashion sales forecasting under conditions of lack of historical data, see Beheshti-Kashi et al (2015). For a recent comprehensive review of computational models that can be applied for fast fashion demand forecasting, see Ren et al (2017).…”

Section: Literature Reviewmentioning

confidence: 99%

A methodology for increasing revenue in fashion retail industry

Nucamendi-Guillén

Moreno

Mendoza

2018

IJRDM

View full text Add to dashboard Cite

Purpose Fashion retail companies typically exhibit short life-cycles, high volatility and low predictability. Therefore, their success is largely determined by the organisation’s flexibility and responsiveness. The purpose of this paper is to present a methodology to facilitate inventory control to minimise both shortages and excess inventory for a multi-product, multi-period finite time horizon inventory problem by using statistical and stochastic analysis. Design/methodology/approach The proposed methodology operates in two phases: the first phase consists on determining an aggregate plan (AP) that will be used for monitoring the behaviour of the items during the time horizon. This plan is obtained by statistically analysing historical data related to sales and inventory shortages and is used to determine a demand forecast during the time horizon that allows to handle with potential disruptions derived from real demand variations. Finally, supply replenishment policies are defined to facilitate the monitoring process during the second phase. For the second phase, the behaviour of real demand for every item is captured into a database and compared against its projected demand (from the AP). If needed, adjustments are made in the procurement of future deliveries to reduce the probability of having shortages and/or excess inventory. Findings A case study in a Mexican fashion retail company was conducted to assess the performance of the methodology. Results indicate that shortage in early periods can be reduced totally for certain products while, for others, the reduction is about 90.5 per cent. In addition, the incomes of the company were increased over 57 per cent. Research limitations/implications Even when the success of the methodology has been shown, cultural and behavioural factors were not considered. An extensive study is suggested to determine if these factors should be included to enhance the performance of the methodology. Practical implications A case study of a Mexican fashion retail company was conducted to assess the performance of the proposed methodology. The methodology is easy to implement and effectively and quickly responds to disruptions in the demand and it also significantly reduces the level of shortages while increasing sales and revenue for the company. Originality/value This paper proposes a methodology that is able to anticipate product’s behaviour from early weeks. Additionally, replenishment policies allow to quickly adjust future orders to guarantee the availability of items and minimise overstock.

show abstract

“…There are several researchers who have to discuss sales forecasting and its application to real-life problems. Samaneh et al [12] did a survey on retail sales forecasting and forecasting in fashion markets. They concluded that conventional forecasting methods face challenges in producing accurate sales data for new products and consumer-oriented goods.…”

Section: Related Workmentioning

confidence: 99%

GPU Implementation of Sales Forecasting with Linear Regression

Yusuf¹,

Alawneh²

2018

IJIRCST

View full text Add to dashboard Cite

Forecasting of sales is very important in any business as it helps managers to learn from historical data and make informed decisions. This generally involves intensive processes using spreadsheets which require inputs from all levels in an organization. This approach introduces bias and is generally not accurate. There are several methods that have been used in the past to forecast sales, such as Exponential Smoothing, Moving Average, and Autoregressive Moving Average (ARMA). Due to the nature of the data, it usually takes more time for these methods to analyze the sales data and make predictions. In this paper, the sales data is analyzed and predictions are made by using linear regression as implemented on the GPU to make the process faster. Sales forecasting is made possible by finding best fit line by linear regression techniques (i.e. linear convolution). To illustrate this process, simulated sales data was used. The sales forecasting with linear regression implementation using GPU was compared to the CPU implementation and a speedup of up to 7.557x was achieved.

show abstract

A survey on retail sales forecasting and prediction in fashion markets

Cited by 76 publications

References 45 publications

The Potential Role of AI in Anticipating Futures from a Design Process Perspective: From the Reflexive Description of “Design” to a Discussion of Influences by the Inclusion of AI in the Futures Research Process

The Potential Role of AI in Anticipating Futures from a Design Process Perspective: From the Reflexive Description of “Design” to a Discussion of Influences by the Inclusion of AI in the Futures Research Process

A methodology for increasing revenue in fashion retail industry

GPU Implementation of Sales Forecasting with Linear Regression

Contact Info

Product

Resources

About