Forecasting sales using online review and search engine data: A method based on PCA–DSFOA–BPNN

Zhang, Chuan; Tian, Yuxin; Fan, Zhi‐Ping

doi:10.1016/j.ijforecast.2021.07.010

Cited by 47 publications

(18 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Secondly, AI-based models generally have problems of overfitting or local optima ( Zhang, Li, MUSKAT, & Law, 2021 ). In contrast, deep learning approaches can extract discriminative features without requiring a lot of human effort and domain knowledge, which has become a research hotspot in recent years ( Bi, Li, & Fan, 2021 ; Kulshrestha et al, 2020 ; Li & Law, 2019 ; Zhang et al, 2020 ).…”

Section: Literature Reviewmentioning

confidence: 99%

“…Such search query data, covering customers’ digital footprints, reflects the consumption preferences and desires of tourists and can be used as a powerful predictor in the prediction. A lot of researches in several areas have explored the role of search query data in the forecasting and these researches can be classified into three categories: industry market ( Chen, Xu, Jia, & Gao, 2021 ; Hand & Judge, 2012 ; Lu, Li, Chai, & Wang, 2020 ; Petropoulos, Siakoulis, Lazaris, & Vlachogiannakis, 2021 ; Yang, Guo, Sun, & Li, 2021 ; Zhang, Tian, & Fan, 2022 ), macroeconomic indicators forecasting ( Smith, 2016 ; Aaronson et al, 2022 ), public health and disease surveillance ( Ginsberg et al, 2009 ; Liu, Feng, Tsui, & Sun, 2021; Song et al, 2014 ). Table 2 summarises the basic information of some representative studies of tourism demand forecasting recent years.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Can multi-source heterogeneous data improve the forecasting performance of tourist arrivals amid COVID-19? Mixed-data sampling approach

Zhao

et al. 2023

Tourism Management

View full text Add to dashboard Cite

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Can multi-source heterogeneous data improve the forecasting performance of tourist arrivals amid COVID-19? Mixed-data sampling approach

Zhao

et al. 2023

Tourism Management

View full text Add to dashboard Cite

“…Multiple attributes are seen to impact customer satisfaction in different ways (Slevitch and Oh, 2010). While identifying these attributes correctly is still a challenge (Piris and Gay, 2021;Zhang et al, 2021), understanding their impact on customer satisfaction is also the focus of growing literature (Srivastava and Kumar, 2021;Sudhakar and Gunasekar, 2020). Studies identify the fact that not all attributes impact customer satisfaction in the same way.…”

Section: Theoretical Backgroundmentioning

confidence: 99%

“…As a reliable source of information (Shan, 2016), consumers read these reviews prior to purchasing a product (Bhattacharyya and Bose, 2020) or booking a hotel room (Vermeulen and Seegers, 2009). Studies have also highlighted the economic value of online reviews for firms (Tirunillai and Tellis, 2012) and their influence on firm sales (Zhang et al, 2021;Chevalier and Mayzlin, 2003) and firm value (Eachempati et al, 2022). Thus, it is advisable for firms to engage in understanding the text reviews written by customers regarding their product purchase experience.…”

Section: Datamentioning

confidence: 99%

AI-enables product purchase on Amazon: what are the consumers saying?

Gunasekar

Ray

Dixit

et al. 2022

View full text Add to dashboard Cite

Purpose This study aims to identify the product attributes that influence customer satisfaction related to AI-enabled products with a strong forecast of growth. This study is very timely as the market for AI-based smart home products is still at a nascent stage in emerging economies (Vaishali Dar, 2021). Adding evidence to literature on the experience of customers, identifying the attributes that lead to customer satisfaction and those that lead to dissatisfaction are essential for products that were launched recently during the pandemic. This study makes valuable addition to the existing literature. Design/methodology/approach Online reviews (12,326 reviews) for EchoDot products launched by Amazon India during the pandemic were collected for the study. The attributes were identified based on the most frequently discussed attributes in the text reviews. Further review valence was determined to group the reviews under positive reviews indicating customer satisfaction and negative reviews indicating customer dissatisfaction. Logistic regression was used to identify the attributes that significantly impact customer satisfaction/dissatisfaction. Findings The results of the study indicate that while EchoDot is seen to add value to the smart home environment (home variable), video (video variable) and speaker (speaker variable) quality also contribute to customer satisfaction. Further, consumers found the product truly worth their money (value for money variable). Other attributes like a complaint about Bluetooth features are seen to increase the probability of customer dissatisfaction. Originality/value This study identifies the most important attributes that influence customer satisfaction in AI-enabled product sales on e-commerce platforms in pandemic times for India. Such studies are scarce in the emerging markets where the AI-based home appliance market is still in its nascent stage, and the customers are trying out their experiences with these products. What the customers expect and are these products fulfill these expectations is an important question that needs to be addressed by research. This study addresses this gap and adds to this literature.

show abstract

“…Backpropagation is a neural network learning algorithm [7]. The field of neural networks was originally ignited by psychologists and neuroscientists who sought to develop and test computational analogs of neurons.…”

Section: Introductionmentioning

confidence: 99%

BPNN Optimization With Genetic Algorithm For Classification of Tobacco Leaves With GLCM Extraction Features

Evandari

Soeleman

Pramunendar

2023

J. RESTI (Rekayasa Sist. Teknol. Inf.)

View full text Add to dashboard Cite

Tobacco leaves are one of the agricultural commodities cultivated by Indonesian farmers. In their application in the field, there are many obstacles in tobacco leaf cultivation, one of which is declining tobacco quality caused by weather factors. In this study, a technology-based analysis step was carried out to determine the classification in determining the quality of tobacco leaves. The research was carried out by applying the classification optimization of the Backpropagation Artificial Neural Network Method and genetic algorithms to determine the weights obtained from extracting GLCM features. You can get the weight value from the genetic algorithm on the homogeneity variable from this analysis step. The variable gets a weight value of 1. The results of this study obtained a classification value with the Backpropagation Artificial Neural Network Method model getting an accuracy value of 53.50% at a hidden layer value of 2,4,5,7. For classification with the Artificial Neural Network Method, Backpropagation, which is optimized with genetic algorithms, you get an accuracy value of 64.50% at the 4th hidden layer value. From this study, the value of optimization accuracy increased by 11% after being optimized with genetic algorithms.

show abstract

Forecasting sales using online review and search engine data: A method based on PCA–DSFOA–BPNN

Cited by 47 publications

References 35 publications

Can multi-source heterogeneous data improve the forecasting performance of tourist arrivals amid COVID-19? Mixed-data sampling approach

Can multi-source heterogeneous data improve the forecasting performance of tourist arrivals amid COVID-19? Mixed-data sampling approach

AI-enables product purchase on Amazon: what are the consumers saying?

BPNN Optimization With Genetic Algorithm For Classification of Tobacco Leaves With GLCM Extraction Features

Contact Info

Product

Resources

About