Matches in SemOpenAlex for { <https://semopenalex.org/work/W2988077807> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W2988077807 abstract "In online channels, products are returned at high rates. Shipping, processing, and refurbishing are so costly that a retailer's profit is extremely sensitive to return rates. In many product categories, such as the $500 billion fashion industry, direct experiments are not feasible because the fashion season is over before sufficient data are observed. We show that predicting return rates prior to product launch enhances profit substantially. Using data from a large European retailer (over 1.5 million transactions for about 4,500 fashion items), we demonstrate that machine-learning methods applied to product images enhance predictive ability relative to the retailer’s benchmark (category, seasonality, price, and color labels). Custom image-processing features (RGB color histograms, Gabor filters) capture color and patterns to improve predictions, but deep-learning features improve predictions significantly more. Deep learning appears to capture color-pattern-shape and other intangibles associated with high return rates for apparel. We derive an optimal policy for launch decisions that takes prediction uncertainty into account. The optimal deep-learning-based policy improves profits, achieving 40% of the improvement that would be achievable with perfect information. We show that the retailer could further enhance predictive ability and profits if it could observe the discrepancy in online and offline sales." @default.
- W2988077807 created "2019-11-22" @default.
- W2988077807 creator A5004593390 @default.
- W2988077807 creator A5032453542 @default.
- W2988077807 creator A5036792000 @default.
- W2988077807 creator A5037511367 @default.
- W2988077807 date "2018-01-01" @default.
- W2988077807 modified "2023-09-23" @default.
- W2988077807 title "Leveraging the Power of Images in Predicting Product Return Rates" @default.
- W2988077807 cites W1529672735 @default.
- W2988077807 cites W1974434592 @default.
- W2988077807 cites W1983004841 @default.
- W2988077807 cites W1988908583 @default.
- W2988077807 cites W2021573668 @default.
- W2988077807 cites W2022920407 @default.
- W2988077807 cites W2032072016 @default.
- W2988077807 cites W2095905764 @default.
- W2988077807 cites W2125148312 @default.
- W2988077807 cites W2129204218 @default.
- W2988077807 cites W2144947015 @default.
- W2988077807 cites W2167647276 @default.
- W2988077807 cites W2183456571 @default.
- W2988077807 cites W2183705853 @default.
- W2988077807 cites W2301613449 @default.
- W2988077807 cites W2892199291 @default.
- W2988077807 cites W2970807495 @default.
- W2988077807 cites W3022128117 @default.
- W2988077807 cites W3040692926 @default.
- W2988077807 cites W3123223435 @default.
- W2988077807 cites W3150177756 @default.
- W2988077807 cites W3163609607 @default.
- W2988077807 cites W3171241005 @default.
- W2988077807 cites W3198767726 @default.
- W2988077807 cites W4230487973 @default.
- W2988077807 doi "https://doi.org/10.2139/ssrn.3209307" @default.
- W2988077807 hasPublicationYear "2018" @default.
- W2988077807 type Work @default.
- W2988077807 sameAs 2988077807 @default.
- W2988077807 citedByCount "5" @default.
- W2988077807 countsByYear W29880778072019 @default.
- W2988077807 countsByYear W29880778072020 @default.
- W2988077807 countsByYear W29880778072021 @default.
- W2988077807 countsByYear W29880778072022 @default.
- W2988077807 crossrefType "journal-article" @default.
- W2988077807 hasAuthorship W2988077807A5004593390 @default.
- W2988077807 hasAuthorship W2988077807A5032453542 @default.
- W2988077807 hasAuthorship W2988077807A5036792000 @default.
- W2988077807 hasAuthorship W2988077807A5037511367 @default.
- W2988077807 hasConcept C149782125 @default.
- W2988077807 hasConcept C162324750 @default.
- W2988077807 hasConcept C41008148 @default.
- W2988077807 hasConceptScore W2988077807C149782125 @default.
- W2988077807 hasConceptScore W2988077807C162324750 @default.
- W2988077807 hasConceptScore W2988077807C41008148 @default.
- W2988077807 hasLocation W29880778071 @default.
- W2988077807 hasOpenAccess W2988077807 @default.
- W2988077807 hasPrimaryLocation W29880778071 @default.
- W2988077807 hasRelatedWork W1973538245 @default.
- W2988077807 hasRelatedWork W2013444265 @default.
- W2988077807 hasRelatedWork W2021570049 @default.
- W2988077807 hasRelatedWork W2030617584 @default.
- W2988077807 hasRelatedWork W2056210026 @default.
- W2988077807 hasRelatedWork W2161519270 @default.
- W2988077807 hasRelatedWork W2899084033 @default.
- W2988077807 hasRelatedWork W3149328373 @default.
- W2988077807 hasRelatedWork W331667891 @default.
- W2988077807 hasRelatedWork W2142213187 @default.
- W2988077807 isParatext "false" @default.
- W2988077807 isRetracted "false" @default.
- W2988077807 magId "2988077807" @default.
- W2988077807 workType "article" @default.