2023 Fiscal Year Final Research Report
Research on Data Analysis Platform for Business Value Creation and Time-Varying Collaborative Filtering
| Project/Area Number |
19K04914
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 25010:Social systems engineering-related
|
|---|
| Research Institution | Waseda University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
平澤 茂一 早稲田大学, 理工学術院, 名誉教授 (30147946)
松嶋 敏泰 早稲田大学, 理工学術院, 教授 (30219430)
|
|---|
| Project Period (FY) |
2019-04-01 – 2024-03-31
|
| Keywords | データ解析プラットフォーム / 潜在構造分析 / 協調フィルタリング / ビッグデータ / 統計的機械学習 |
|---|
| Outline of Final Research Achievements |
In this research, we constructed a platform (DAPF) that enables the analysis of proprietary big data held by companies in a secure environment on a server without exporting the data outside the server. The cloud DAPF effectively conducted practical operations in a total of five projects that analyzed real data. Furthermore, the on-premise DAPF verified scalability, such as multiple analysis environments using containers and external connections via VPN.
Regarding collaborative filtering, we proposed a latent structure model that assumes multiple latent variables for various types of data, including customer and product attribute information, time information, and consumption behavior. This model integrates these data by considering the relationships between the observed and latent variables. We also evaluated the effectiveness of this model.
|
| Free Research Field |
統計的学習理論
|
| Academic Significance and Societal Importance of the Research Achievements |
企業の持つビッグデータを大学の研究者が安全に分析を行うプラットフォームは，企業にとっては新たな価値創造の機会として，大学の研究者にとっては学術研究の発展のために大いに役立つ．この時外部へデータを漏洩させない仕組みが非常に重要である．また個人（ユーザ）が商品（サービス）に対して行う日々の消費行動について，それぞれに対する潜在変数と観測変数の関係としてある種の統合的な視点でモデル化及び推定を行う方法を示した本研究は，学術的および社会的な観点の両者に対して意義がある．
|
