Changes
On January 2, 2025 at 11:32:02 PM UTC,
-
Changed value of field
doi_status
toTrue
in Sales Forecast in E-commerce using Convolutional Neural Network -
Changed value of field
doi_date_published
to2025-01-02
in Sales Forecast in E-commerce using Convolutional Neural Network -
Added resource Original Metadata to Sales Forecast in E-commerce using Convolutional Neural Network
f | 1 | { | f | 1 | { |
2 | "access_rights": "", | 2 | "access_rights": "", | ||
3 | "author": "Kui Zhao", | 3 | "author": "Kui Zhao", | ||
4 | "author_email": "", | 4 | "author_email": "", | ||
5 | "citation": [], | 5 | "citation": [], | ||
6 | "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700", | 6 | "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700", | ||
7 | "defined_in": "https://doi.org/10.48550/arXiv.1708.07946", | 7 | "defined_in": "https://doi.org/10.48550/arXiv.1708.07946", | ||
8 | "doi": "10.57702/w9rff3f7", | 8 | "doi": "10.57702/w9rff3f7", | ||
n | 9 | "doi_date_published": null, | n | 9 | "doi_date_published": "2025-01-02", |
10 | "doi_publisher": "TIB", | 10 | "doi_publisher": "TIB", | ||
n | 11 | "doi_status": false, | n | 11 | "doi_status": true, |
12 | "domain": "https://service.tib.eu/ldmservice", | 12 | "domain": "https://service.tib.eu/ldmservice", | ||
13 | "extra_authors": [ | 13 | "extra_authors": [ | ||
14 | { | 14 | { | ||
15 | "extra_author": "Can Wang", | 15 | "extra_author": "Can Wang", | ||
16 | "orcid": "" | 16 | "orcid": "" | ||
17 | } | 17 | } | ||
18 | ], | 18 | ], | ||
19 | "groups": [ | 19 | "groups": [ | ||
20 | { | 20 | { | ||
21 | "description": "", | 21 | "description": "", | ||
22 | "display_name": "Convolutional Neural Networks", | 22 | "display_name": "Convolutional Neural Networks", | ||
23 | "id": "acd07bab-4528-49f3-984f-03cf9614b5ab", | 23 | "id": "acd07bab-4528-49f3-984f-03cf9614b5ab", | ||
24 | "image_display_url": "", | 24 | "image_display_url": "", | ||
25 | "name": "convolutional-neural-networks", | 25 | "name": "convolutional-neural-networks", | ||
26 | "title": "Convolutional Neural Networks" | 26 | "title": "Convolutional Neural Networks" | ||
27 | }, | 27 | }, | ||
28 | { | 28 | { | ||
29 | "description": "", | 29 | "description": "", | ||
30 | "display_name": "E-commerce", | 30 | "display_name": "E-commerce", | ||
31 | "id": "3c9967b4-b6f1-45c0-9b35-29bbdb130778", | 31 | "id": "3c9967b4-b6f1-45c0-9b35-29bbdb130778", | ||
32 | "image_display_url": "", | 32 | "image_display_url": "", | ||
33 | "name": "e-commerce", | 33 | "name": "e-commerce", | ||
34 | "title": "E-commerce" | 34 | "title": "E-commerce" | ||
35 | } | 35 | } | ||
36 | ], | 36 | ], | ||
37 | "id": "c0118e42-f491-4ba0-9d2e-6a2e14ec3921", | 37 | "id": "c0118e42-f491-4ba0-9d2e-6a2e14ec3921", | ||
38 | "isopen": false, | 38 | "isopen": false, | ||
39 | "landing_page": "https://tianchi.aliyun.com/competition/", | 39 | "landing_page": "https://tianchi.aliyun.com/competition/", | ||
40 | "license_title": null, | 40 | "license_title": null, | ||
41 | "link_orkg": "", | 41 | "link_orkg": "", | ||
42 | "metadata_created": "2025-01-02T23:32:01.026419", | 42 | "metadata_created": "2025-01-02T23:32:01.026419", | ||
n | 43 | "metadata_modified": "2025-01-02T23:32:01.026424", | n | 43 | "metadata_modified": "2025-01-02T23:32:01.693861", |
44 | "name": | 44 | "name": | ||
45 | "sales-forecast-in-e-commerce-using-convolutional-neural-network", | 45 | "sales-forecast-in-e-commerce-using-convolutional-neural-network", | ||
46 | "notes": "Sales forecast is an essential task in E-commerce and has | 46 | "notes": "Sales forecast is an essential task in E-commerce and has | ||
47 | a crucial impact on making informed business decisions. It can help us | 47 | a crucial impact on making informed business decisions. It can help us | ||
48 | to manage the workforce, cash flow and resources such as optimizing | 48 | to manage the workforce, cash flow and resources such as optimizing | ||
49 | the supply chain of manufacturers etc. Sales forecast is a challenging | 49 | the supply chain of manufacturers etc. Sales forecast is a challenging | ||
50 | problem in that sales is affected by many factors including promotion | 50 | problem in that sales is affected by many factors including promotion | ||
51 | activities, price changes, and user preferences etc. Traditional sales | 51 | activities, price changes, and user preferences etc. Traditional sales | ||
52 | forecast techniques mainly rely on historical sales data to predict | 52 | forecast techniques mainly rely on historical sales data to predict | ||
53 | future sales and their accuracies are limited. Some more recent | 53 | future sales and their accuracies are limited. Some more recent | ||
54 | learning-based methods capture more information in the model to | 54 | learning-based methods capture more information in the model to | ||
55 | improve the forecast accuracy. However, these methods require | 55 | improve the forecast accuracy. However, these methods require | ||
56 | case-by-case manual feature engineering for specific commercial | 56 | case-by-case manual feature engineering for specific commercial | ||
57 | scenarios, which is usually a difficult, time-consuming task and | 57 | scenarios, which is usually a difficult, time-consuming task and | ||
58 | requires expert knowledge. To overcome the limitations of existing | 58 | requires expert knowledge. To overcome the limitations of existing | ||
59 | methods, we propose a novel approach in this paper to learn effective | 59 | methods, we propose a novel approach in this paper to learn effective | ||
60 | features automatically from the structured data using the | 60 | features automatically from the structured data using the | ||
61 | Convolutional Neural Network (CNN). When fed with raw log data, our | 61 | Convolutional Neural Network (CNN). When fed with raw log data, our | ||
62 | approach can automatically extract effective features from that and | 62 | approach can automatically extract effective features from that and | ||
63 | then forecast sales using those extracted features. We test our method | 63 | then forecast sales using those extracted features. We test our method | ||
64 | on a large real-world dataset from CaiNiao.com and the experimental | 64 | on a large real-world dataset from CaiNiao.com and the experimental | ||
65 | results validate the effectiveness of our method.", | 65 | results validate the effectiveness of our method.", | ||
n | 66 | "num_resources": 0, | n | 66 | "num_resources": 1, |
67 | "num_tags": 4, | 67 | "num_tags": 4, | ||
68 | "organization": { | 68 | "organization": { | ||
69 | "approval_status": "approved", | 69 | "approval_status": "approved", | ||
70 | "created": "2024-11-25T12:11:38.292601", | 70 | "created": "2024-11-25T12:11:38.292601", | ||
71 | "description": "", | 71 | "description": "", | ||
72 | "id": "079d46db-32df-4b48-91f3-0a8bc8f69559", | 72 | "id": "079d46db-32df-4b48-91f3-0a8bc8f69559", | ||
73 | "image_url": "", | 73 | "image_url": "", | ||
74 | "is_organization": true, | 74 | "is_organization": true, | ||
75 | "name": "no-organization", | 75 | "name": "no-organization", | ||
76 | "state": "active", | 76 | "state": "active", | ||
77 | "title": "No Organization", | 77 | "title": "No Organization", | ||
78 | "type": "organization" | 78 | "type": "organization" | ||
79 | }, | 79 | }, | ||
80 | "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559", | 80 | "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559", | ||
81 | "private": false, | 81 | "private": false, | ||
82 | "relationships_as_object": [], | 82 | "relationships_as_object": [], | ||
83 | "relationships_as_subject": [], | 83 | "relationships_as_subject": [], | ||
t | 84 | "resources": [], | t | 84 | "resources": [ |
85 | { | ||||
86 | "cache_last_updated": null, | ||||
87 | "cache_url": null, | ||||
88 | "created": "2025-01-03T00:16:29", | ||||
89 | "data": [ | ||||
90 | "dcterms:title", | ||||
91 | "dcterms:accessRights", | ||||
92 | "dcterms:creator", | ||||
93 | "dcterms:description", | ||||
94 | "dcterms:issued", | ||||
95 | "dcterms:language", | ||||
96 | "dcterms:identifier", | ||||
97 | "dcat:theme", | ||||
98 | "dcterms:type", | ||||
99 | "dcat:keyword", | ||||
100 | "dcat:landingPage", | ||||
101 | "dcterms:hasVersion", | ||||
102 | "dcterms:format", | ||||
103 | "mls:task", | ||||
104 | "datacite:isDescribedBy" | ||||
105 | ], | ||||
106 | "description": "The json representation of the dataset with its | ||||
107 | distributions based on DCAT.", | ||||
108 | "format": "JSON", | ||||
109 | "hash": "", | ||||
110 | "id": "f6c2eb13-185a-435d-b94a-43d6bc14b077", | ||||
111 | "last_modified": "2025-01-02T23:32:01.686292", | ||||
112 | "metadata_modified": "2025-01-02T23:32:01.696744", | ||||
113 | "mimetype": "application/json", | ||||
114 | "mimetype_inner": null, | ||||
115 | "name": "Original Metadata", | ||||
116 | "package_id": "c0118e42-f491-4ba0-9d2e-6a2e14ec3921", | ||||
117 | "position": 0, | ||||
118 | "resource_type": null, | ||||
119 | "size": 2065, | ||||
120 | "state": "active", | ||||
121 | "url": | ||||
122 | resource/f6c2eb13-185a-435d-b94a-43d6bc14b077/download/metadata.json", | ||||
123 | "url_type": "upload" | ||||
124 | } | ||||
125 | ], | ||||
85 | "services_used_list": "", | 126 | "services_used_list": "", | ||
86 | "state": "active", | 127 | "state": "active", | ||
87 | "tags": [ | 128 | "tags": [ | ||
88 | { | 129 | { | ||
89 | "display_name": "Convolutional Neural Networks", | 130 | "display_name": "Convolutional Neural Networks", | ||
90 | "id": "a167095b-f2a5-4c27-8f27-c413611cc4ee", | 131 | "id": "a167095b-f2a5-4c27-8f27-c413611cc4ee", | ||
91 | "name": "Convolutional Neural Networks", | 132 | "name": "Convolutional Neural Networks", | ||
92 | "state": "active", | 133 | "state": "active", | ||
93 | "vocabulary_id": null | 134 | "vocabulary_id": null | ||
94 | }, | 135 | }, | ||
95 | { | 136 | { | ||
96 | "display_name": "E-commerce", | 137 | "display_name": "E-commerce", | ||
97 | "id": "6f70e242-0f92-47a9-87c4-e4b9b2a62e2c", | 138 | "id": "6f70e242-0f92-47a9-87c4-e4b9b2a62e2c", | ||
98 | "name": "E-commerce", | 139 | "name": "E-commerce", | ||
99 | "state": "active", | 140 | "state": "active", | ||
100 | "vocabulary_id": null | 141 | "vocabulary_id": null | ||
101 | }, | 142 | }, | ||
102 | { | 143 | { | ||
103 | "display_name": "Machine Learning", | 144 | "display_name": "Machine Learning", | ||
104 | "id": "c4f3defc-ca48-45a9-9217-ce35bd3ed73c", | 145 | "id": "c4f3defc-ca48-45a9-9217-ce35bd3ed73c", | ||
105 | "name": "Machine Learning", | 146 | "name": "Machine Learning", | ||
106 | "state": "active", | 147 | "state": "active", | ||
107 | "vocabulary_id": null | 148 | "vocabulary_id": null | ||
108 | }, | 149 | }, | ||
109 | { | 150 | { | ||
110 | "display_name": "Sales Forecasting", | 151 | "display_name": "Sales Forecasting", | ||
111 | "id": "95682625-b948-4007-ad4b-03d7568ca540", | 152 | "id": "95682625-b948-4007-ad4b-03d7568ca540", | ||
112 | "name": "Sales Forecasting", | 153 | "name": "Sales Forecasting", | ||
113 | "state": "active", | 154 | "state": "active", | ||
114 | "vocabulary_id": null | 155 | "vocabulary_id": null | ||
115 | } | 156 | } | ||
116 | ], | 157 | ], | ||
117 | "title": "Sales Forecast in E-commerce using Convolutional Neural | 158 | "title": "Sales Forecast in E-commerce using Convolutional Neural | ||
118 | Network", | 159 | Network", | ||
119 | "type": "dataset", | 160 | "type": "dataset", | ||
120 | "version": "" | 161 | "version": "" | ||
121 | } | 162 | } |