On the Use of Learning-Based Forecasting Methods for Ameliorating Fashion Business Processes: A Position Paper

Skenderi, Geri; Joppi, Christian; Denitto, Matteo; Cristani, Marco

doi:10.1007/978-3-031-37742-6_50

Cited by 2 publications

(4 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The final task also employs topic modeling as an auxiliary tool. We will utilize a Transformerbased forecasting model, as used in the previous research [14], to assess its performance by incorporating reviews as input data for the decoder and utilizing product features extracted through topic modeling.…”

Section: Methodsmentioning

confidence: 99%

“…Study [14] attempted to predict product sales data. This study injected product information extracted from additional data about products into the decoder of basic transformer.…”

Section: Transformer-based Time Series Forecastingmentioning

confidence: 99%

“…In the context of sales forecasting, the model employed is fundamentally based on a modification of the Transformer architecture, which was adapted from the structure proposed in a previous study for sales prediction [14]. For the initial input to the encoder, we use search volume time series data spanning 157 weeks from 2019 to 2021, associated with product keywords and their respective categories.…”

Section: E Trend Forecastingmentioning

confidence: 99%

See 2 more Smart Citations

Topic Modeling-Based Framework for Extracting Marketing Information From E-Commerce Reviews

An,

Kim,

Lee

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Reviews left by consumers on e-commerce platforms provide crucial marketing information as they are a publicly available source of information providing insight into consumers' thoughts and opinions. However, it is physically impossible to read hundreds of reviews per product. Therefore, algorithmically extracting the necessary insights from a large volume of review data can provide more advanced information while reducing time and costs. This study aims to automate the process of extracting consumer intentions, related products, pros and cons of products, and trend forecasting from review data using clustering algorithms. The review dataset was constructed by selecting 17 products on the Naver Shopping platform and crawling them. Various clustering-based algorithms such as Deep Clustering Network, BERTopic, and a Transformer-based forecasting model were used to conduct the research. It is expected that this will allow for a more accurate understanding of consumer thoughts, which can be utilized in marketing for various products and services.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Study [14] attempted to predict product sales data. This study injected product information extracted from additional data about products into the decoder of basic transformer.…”

Section: Transformer-based Time Series Forecastingmentioning

confidence: 99%

Section: E Trend Forecastingmentioning

confidence: 99%

See 1 more Smart Citation

Topic Modeling-Based Framework for Extracting Marketing Information From E-Commerce Reviews

An,

Kim,

Lee

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…For example, Choi et al (2012) proposed an algorithm to predict time-series data of various economic indicators for the sales industry using the internet search volume of some keywords. Skenderi et al (2021) conducted sales trend prediction in the fashion industry. Sayyad et al (2009) predicted trends in events using the frequency of occurrence for a set of keywords that refer to an event and story as explanatory variables.…”

Section: Related Workmentioning

confidence: 99%

Construction of Evaluation Datasets for Trend Forecasting Studies

Matsuno

Mizuki

Sakaki

2023

ICWSM

View full text Add to dashboard Cite

In this study, we discuss issues in the traditional evaluation norms of trend forecasts, outline a suitable evaluation method, propose an evaluation dataset construction procedure, and publish Trend Dataset: the dataset we have created. As trend predictions often yield economic benefits, trend forecasting studies have been widely conducted. However, a consistent and systematic evaluation protocol has yet to be adopted. We consider that the desired evaluation method would address the performance of predicting which entity will trend, when a trend occurs, and how much it will trend based on a reliable indicator of the general public's recognition as a gold standard. Accordingly, we propose a dataset construction method that includes annotations for trending status (trending or non-trending), degree of trending (how well it is recognized), and the trend period corresponding to a surge in recognition rate. The proposed method uses questionnaire-based recognition rates interpolated using Internet search volume, enabling trend period annotation on a weekly timescale. The main novelty is that we survey when the respondents recognize the entities that are highly likely to have trended and those that haven't. This procedure enables a balanced collection of both trending and non-trending entities. We constructed the dataset and verified its quality. We confirmed that the interests of entities estimated using Wikipedia information enables the efficient collection of trending entities a priori. We also confirmed that the Internet search volume agrees with public recognition rate among trending entities.

show abstract

On the Use of Learning-Based Forecasting Methods for Ameliorating Fashion Business Processes: A Position Paper

Cited by 2 publications

References 23 publications

Topic Modeling-Based Framework for Extracting Marketing Information From E-Commerce Reviews

Topic Modeling-Based Framework for Extracting Marketing Information From E-Commerce Reviews

Construction of Evaluation Datasets for Trend Forecasting Studies

Contact Info

Product

Resources

About