Junichiro Niimi

Junichiro Niimi
Meijo University · Department of Business Management

Doctor of Economics
Looking for the fun from Japan.

About

15
Publications
8,623
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
26
Citations
Citations since 2016
12 Research Items
26 Citations
201620172018201920202021202202468101214
201620172018201920202021202202468101214
201620172018201920202021202202468101214
201620172018201920202021202202468101214
Introduction
Dr. Junichiro NIIMI is the marketing/data science researcher in Tokyo, Japan. He studied at Nagoya University, Japan and completed Doctor of Economics in March, 2018. Now belonged to RIKEN AIP (AIP: center for Advanced Intelligence Project) which is Japanese bridgehead in leading AI/statistics research, and now working on the better prediction on consumer behaviors.
Additional affiliations
April 2022 - present
Meijo University
Position
  • Professor (Associate)
April 2020 - present
RIKEN
Position
  • Researcher
April 2019 - March 2022
Meijo University
Position
  • Professor (Assistant)
Education
April 2015 - March 2018
Nagoya University
Field of study
  • Marketing Science
April 2013 - March 2015
Nagoya University
Field of study
  • Marketing Science
April 2009 - March 2013
Nagoya University
Field of study
  • Finance

Publications

Publications (15)
Conference Paper
Full-text available
This study examines the impact of consumers' short-term intensive use of smartphone games on behavioral loyalty. In recent, short-term usage called clumpiness has received increasing attentions. However, if we utilize the indice in order to capture those short-term intensive use, several problems pop up. In this presentation, we sort the problems i...
Article
Full-text available
Background Public perceptions and personal characteristics are heterogeneous between countries and subgroups, which may have different impacts on health-protective behaviors during the coronavirus disease 2019 (COVID-19) pandemic. To assess whether self-reported perceptions of COVID-19 and personal characteristics are associated with protective beh...
Preprint
Full-text available
Background: Public perceptions and personal characteristics are heterogeneous between countries and subgroups, which may have different impacts on health-protective behaviors during the coronavirus disease 2019 (COVID-19) pandemic. To assess whether self-reported perceptions of COVID-19 and personal characteristics are associated with protective be...
Article
In recent, the concept of clumpiness has received increasing attention as a novelmethod called RFMC in Customer Relationship Management (CRM). However, it hasbeen not so long since clumpiness is proposed, there still remains difficulties. In thispaper we firstly identify the problems of clumpiness in both statistical and practicalfields, propose th...
Article
In recent, the concept of clumpiness has received increasing attention as a novel method called RFMC in Customer Relationship Management (CRM). However, it has been not so long since clumpiness is proposed, there still remains difficulties. In this paper we firstly identify the problems of clumpiness in both statistical and practical fields, propos...
Article
Full-text available
In recent, the concept of clumpiness has received increasing attention as a novel method called RFMC in Customer Relationship Management (CRM). However, it has been not so long since clumpiness is proposed, there still remains difficulties. In this paper we firstly identify the problems of clumpiness in both statistical and practical fields, propos...
Article
Full-text available
Both in academia and practice various methods of Customer Relationship Management (CRM) have been in use especially RFMC (Zhang et al., 2014) which is recently proposed as a novel method due to its high performance of predicting competitive purchase. However, it still has difficulty identifying consumer heterogeneity compared to variety variables p...
Conference Paper
Full-text available
Nowadays it is difficult for companies to formulate marketing strategy without considering their customers behavior in competing �rms. However, even in the big data era, combining large scale data in the company and the general lifestyle survey data is still tough. In this research we created the data fusion model with Deep Boltzmann Machine to com...
Article
Full-text available
Nowadays, along with the popularity of E-Commerce, the marketing strategy of retail stores has been more complicated with O2O or Omni-Channel. Therefore, Customer Relationship Management (CRM) is one of the important issue for the retail stores. It can be difficult to predict customers future behavior with the simple quantitive information such as...
Article
Full-text available
Nowadays, along with the popularity of E-Commerce, the marketing strategy of retail stores has been more complicated with O2O or Omni-channel. Therefore, Customer Relationship Management (CRM) is one of the important issue for the retail stores. It can be difficult to predict customers future behavior with the simple quantitive information such as...
Article
Full-text available
It is important for the companies to get much information about their customers. For example, the information that how often each customer purchases from the competitors can be useful when we plan the promotion strategy. In this paper, we focus on the web services and predict customers' behaviors such as browses and purchases in two companies and t...
Article
Full-text available
It is important for the companies to get much information about their customers. For example, the information that how often each customer purchases from the competitors can be useful when we plan the promotion strategy. In this paper, we focus on the web services and predict customers' behaviors such as browses and purchases in two companies...

Questions

Questions (5)
Question
Hi there, I'm so appreciated you pay attentions to this question.
Nowadays, it is quite common that we consider masking or padding when dealing with the data including missing values on sequential data on RNN (or perhaps on image data on CNN).
However, I have not found the paper to propose/establish the exact method.
The reason why I'm looking for it is that I would like to learn what exact happens in RNN to LSTM layer when it is masked as 'Skip the input' .
If you know of any, please let me know.
Thanks from Japan.
Question
In these days, the "feature fusion" in deep neural networks became so popular that many of the academic papers implement it without references.
So, could you please recommend some papers dealing with the effects of feature fusion (i.e., concatenating the hidden layers/multiple inputs), or forking the network (for multiple outputs) ?
Papers in any fields are welcome.
Appreciated for your attention.
Question
Hi, now I'm looking for existing literatures to apply Cox Proportional Hazards Model as survival analysis to customer churn predictions in marketing field.
Customer churn prediction is important in terms of Customer Relationship Management (CRM) and can be applied to following fields:
- Continuous service (such as )
- Continuous product (such as mobile apps)
- E-Commerce (such as Amazon, e-bay)
- Retailers (such as supermarket)
Do you have any suggestion?
Question
Hi, now I'm facing new problem at the construction of neural network in tensotflow.
I would like to implement regression/classification problem at a same time in one neural network, which has two outputs, one for the classification [discrete variable as 0 or 1] and the other for the regression [continuous positive variable like time or length]. This kind of network shares any weights and biases for the several outputs.
In the deepnet library, I can construct this kind of network by jointly locating multiple layers (sigmoid and ReLU) for the output like multi-modal network, however, does anyone know how to do it with Tensorflow?
Question
Does anyone know good Gaussian Bernoulli Deep Boltzmann Machine (GBDBM) library which is easy to modify? I have used deepnet by Nitish Srivastava (https://github.com/nitishsrivastava/deepnet) for several years but it is no longer maintained. So it is better if available in Tensorflow.
Thank you.

Network

Cited By

Projects

Project (1)
Project
We focus on "Clumpiness" as an indicator, which can be easily calculated from the behavior log data.