Development of the NMF based on an action history and questionnaire mixed data for exploratory understanding of a relationship between buying behavior and consumer mind
| Project/Area Number |
17H06779
|
|---|
| Research Category |
Grant-in-Aid for Research Activity Start-up
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
Commerce
|
|---|
| Research Institution | Kyoto University |
|---|
Principal Investigator |
Abe Hiroyasu 京都大学, 医学研究科, 助教 (40807963)
|
|---|
| Project Period (FY) |
2017-08-25 – 2019-03-31
|
| Project Status |
Completed (Fiscal Year 2018)
|
| Budget Amount *help |
¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2018: ¥390,000 (Direct Cost: ¥300,000、Indirect Cost: ¥90,000)
Fiscal Year 2017: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
|
|---|
| Keywords | 探索的データ解析 / 非負値行列因子分解 / ウェブ閲覧履歴 / デモグラフィック属性 / 計算時間 / 購買行動 / 心理 / 商学 / 統計学 / 探索的データ分析 |
|---|
| Outline of Final Research Achievements |
In this study, we developed the new exploratory data analysis method for understanding of a relationship between buying behavior and consumer attribute or mind using action history data, such as buying history or web access, and questionnaire mixed data. The new method is an expansion of the matrix decomposition method that is called nonnegative matrix factorization. We can obtain by the new method some action patterns and characteristics of the some users that did not act according to the patterns. We apply the new method to the real web access log data with user attribute information in a certain shopping website and we confirmed that the new method has potential to get the interpretation as expected. For example, we can grasp a potential needs and identify some users who may not have the potential needs.
|
| Academic Significance and Societal Importance of the Research Achievements |
全ての要素が0以上の値であるようなデータと，質問紙データを組み合わせた汎用性のあるデータ解析手法を開発したことは，学術的意義があると自負する．一方で，本研究の社会的意義としては，より繊細なマーケティング施策を行うための材料を提供できる点にあると考える．開発手法は，行動パターンによって記述されるユーザセグメントを抽出しつつ，そのセグメントが示すパターン通りに行動をしない特異ユーザも抽出できる．このことは，ウェブページ推薦といった潜在ニーズを掘り起こすための施策において，抽出パターンに沿った施策を十把一絡げに行うのではなく，その特異ユーザに対しては柔軟に対応できることにつながる．
|
Report
(3 results)
Research Products
(10 results)
