Papers by Takashi Namatame
2016 Future Technologies Conference (FTC)
Recently, reviews of goods are one of the important factors which have an influence on the consum... more Recently, reviews of goods are one of the important factors which have an influence on the consumer's buying behavior. Under the situation, information aggregation of reviews has attracted much attention in electronic commerce (EC) site. In this study we propose a review recommendation system target on golf EC site. In our proposal system, reviews are scored by the evaluation of characteristic words which were obtained by TF-IDF and reputation analysis. Moreover, our proposal system visualize concurrent network using concurrent relations between the characteristic words. In order to verify the effectiveness of our proposal system, we conducted an experimental evaluation. In the experimental evaluation, we compared our proposal reviews with other review (selected randomly, recently date and reference counts). As the result, it was found that the result score of our proposed reviews were almost the same as the result score of reference count. Moreover, we received positive evaluation about concurrent network. Through these experimental evaluate, we consider that the effectiveness of this system was successfully verified.
Lecture Notes in Computer Science, 2019
For consumer market, it is important fact that the BtoC-EC (business-to-consumer electronic-comme... more For consumer market, it is important fact that the BtoC-EC (business-to-consumer electronic-commerce) market continues to grow. One of the effective marketing strategies is “reciprocal customer transfer” which a store introduces the store’s customers to another store to obtain customer loyalty. In this study, we analyze for effective reciprocal customer transfer between a golf course reservation site and a golf EC site to promote customer’s upsell. Firstly, we divided golf courses into 32 categories and the golf items into 40 categories. Next, we extracted the user’s usage history of these two services. Then, using these data, we carried out the time series association analysis. As a result of the analysis, we found some characteristic rules.
International Journal of Advanced Computer Science and Applications, 2022
Since the early 2000s, the Internet has become increasingly popular for the development of inform... more Since the early 2000s, the Internet has become increasingly popular for the development of information dissemination technology and as a platform for interaction. Therefore, the penetration rate of Social Networking Services (SNSs) is also increasing. Using the accounts created on SNSs, companies can disseminate information and communicate with users on SNSs for marketing purposes. Moreover, there are several influencer marketing activities that use influencers who are highly influential in their surroundings as marketing using SNSs. In this study, we aim to identify influencers on Twitter and consumer network structures for six cosmetic brands. Specifically, create a consumer network for each of the six cosmetic brands using follower data obtained from Twitter is created to identify the network structure. Furthermore, brand influencers were also identified. The consumer network of all six cosmetic brands was created to identify the influencers in the cosmetics industry. We compared the influencers of the brands with the influencers of the entire industry to examine any differences.
Social Computing and Social Media. Human Behavior, 2017
In recent years, acquisition of repeat customers is emphasized for EC sites. On the other hand, t... more In recent years, acquisition of repeat customers is emphasized for EC sites. On the other hand, the defection rate from the first purchase to the second purchase is the highest. There are much attention to acquire the repeat customers in the EC sites in this situation. The purpose of this study is to clarify factors necessary for acquiring repeat customers. Especially, we construct models that predict whether or not to repurchase within a certain period using membership information variables, purchase behavior variables and web browsing behavior variables. Using these models, we extract characteristics relate to presence or absence of repurchase and propose marketing measures to promote to repurchase.
Lecture Notes in Computer Science, 2019
Customer reviews have a major impact on consumers who are considering purchasing and using. There... more Customer reviews have a major impact on consumers who are considering purchasing and using. There are various reviews, such as positive reviews and negative reviews. Consumers who are considering purchasing can obtain useful information without actually using products or shops by looking at the reviews. Moreover, it is possible to grasp the consumer’s actual opinion from the customer review. In this study, we will grasp the characteristics of each golf course for the review on the golf course of a certain golf portal site. In addition, we clarify what kind of change in feature appears due to the difference in golfer skill.
Lecture Notes in Computer Science, 2018
Social networking service (SNS) is very popular in our lives, with expanding internet environment... more Social networking service (SNS) is very popular in our lives, with expanding internet environments and mobile device. Through the SNS, user can submit their opinion or reputation freely, anytime and anywhere. These activities are getting great attention on a various business scenes in recently. Twitter is one of the most popular SNS, and used by numerous people in the world. In addition, since various information is posted on Twitter, it is expected to be utilized as a business strategy, and there have been many studies on the marketing using Twitter data. Moreover, we can get some information about user's network in Twitter. In this research, we attempt to evaluate the network structure using similarity of post on Twitter. We created the user network using similarity of posts mentioned about four titles of Japanese TV drama, and we grasped the post categories that is easy to get user's interest. From the result, we discussed the difference between TV drama and suggestions for promotion strategies of TV drama production company.
Lecture Notes in Computer Science, 2019
In recent years, with expansion and growth of electronic commerce (EC) market, it is expected tha... more In recent years, with expansion and growth of electronic commerce (EC) market, it is expected that the competition of getting customers will be fierce. The EC company is required to find new customers who have the potential of becoming loyal customers as soon as possible. In this study, we analyze customers' behavior using customer membership information data, purchase records data and web access logs data on a golf EC site. Firstly, we evaluate the loyalty of customers using RFM analysis to divide customers into the loyal and general ones. Next, we perform logistic regression to discriminate loyalty by using the first-time purchase and browsing behaviors. Through our analysis, we built a model to predict loyal customers and clarify the characteristic behaviors of high loyal customers.
Lecture Notes in Computer Science, 2019
In recent years, with the needs of TV viewing change in Japan. TV viewing changes from long time ... more In recent years, with the needs of TV viewing change in Japan. TV viewing changes from long time to short time. In order to prevent the viewing time from decreasing as it is, the need to predict customers' taste for TV viewing is increasing. This research focuses on several types of TV viewing, i.e. real time and time shift viewing, in addition, web browsing of customers in view of television viewing is considered. We will grasp the viewing tendency of the customer and predict the TV viewing of customers.
Due to the spread of the electronic commerce site (EC site), it changed to an era where shopping ... more Due to the spread of the electronic commerce site (EC site), it changed to an era where shopping can be done without going to a real store through the Internet. Under these circumstances, a review is one of the important information to consider purchasing at the EC site. In this study, we use the reviews posted on golf portal site and we analyze the characteristic of products using a text mining method. Moreover, we extracted characteristic words and we evaluated 6 products of golf.
In recent years, in the apparel industry, the EC market and SNSs have been expanding. Then it is ... more In recent years, in the apparel industry, the EC market and SNSs have been expanding. Then it is needed a marketing strategy considering the needs of customers. In this study, we aim to identify fashion brands related to similar brands and customer growth (named “key brands”) which promote brand transition using a questionnaire data targeting about 30,000 monitors. Specifically, we used questions about consumption values and favorite fashion brands. We conducted the factor analysis using the question items to obtain potential factors of consumption values. Next, we classify monitors based on the result of factor analysis. Then, we aggregate question about favorite fashion brands and reveal key brands at each age and cluster. Finally, we compare to similar brands from questionnaire data with similar brands from tweet data from Twitter.
Journal of Japan Society for Fuzzy Theory and Intelligent Informatics, 2011
Proceedings of the International Symposium on the Analytic Hierarchy Process, 2003
In this paper, we propose a method for group decision-making using the AHP concept. We focus on o... more In this paper, we propose a method for group decision-making using the AHP concept. We focus on opinion modification in discussion processes and propose a method for obtaining agreement in a group using interactive discussion. Our method is divided into three processes: preparation, opinion declaration and opinion modification. Moreover, to modify opinions, we show quantitative information on the effect of change in term of pairwise value. By showing the information for modifying opinions and making the criterion for agreement explicit, the members who participated in our experimental example were able to reach a satisfying.
In this paper, we predict purchase from access log data and consider customer behavior about purc... more In this paper, we predict purchase from access log data and consider customer behavior about purchase sign on E-commerce site. In addition, applying Convolutional neural networks to this study, we discuss probability of purchase or not purchase and data preprocessing. By extracting hidden layer of model, we consider customer behaviors about purchase and not purchase. Furthermore, we discuss the way of transforming no image datasets to image-like data. We think about probability of using its networks for no images data through this study.
SVM is known as sophisticated classifying model because of kernel trick. The kernel function in t... more SVM is known as sophisticated classifying model because of kernel trick. The kernel function in the SVM formula allows the algorithm to fit the maximum-margin hyperplane in mapped feature space. Therefore SVM model can deal with complex non-linear structure and this feature may contribute to the advantage of SVM model classification. However, in real-world context, we hardly have applications because of the difficulty in semantic interpretation. In this paper, we propose a semantic interpretation method using both LS-SVM and Decision Tree model. Furthermore, we show the validity of the method by analyzing artificial samples and real financial market data.
The spread of Social Networking Services (SNSs) changes personal communication around the world r... more The spread of Social Networking Services (SNSs) changes personal communication around the world rapidly in recent years and the impact has affected the business field. Then many companies approach their consumers by using SNS, but those marketing effects are completely different depending on each community structure. Especially, there is a large difference in the cost that diffuses the information transmitted when the community is concentrated or scattered. It is important to perform a marketing approach that considers the community structure of each company. In this study, we use a brand in the fashion market to detect consumer community structure on SNSs. In addition, based on the formed community, we clarify the characteristic of each community by using posted contents posted by consumers and suggest the method of promotion to consumers via SNSs.
For retail industry such as supermarket and convenience store, it is important to understand cust... more For retail industry such as supermarket and convenience store, it is important to understand customers. In marketing perspective, to match marketing activity to customer needs is one of the most important strategy for retail industry. In this study, we focus on trade area of retail store. If we can grasp the trade size of a store, manager can plan optimal strategy, e.g. how to spend for advertise activity and where we should open a new store. In this study, we use ID-POS data which is the purchase record with customer identification data of a super market chain and calculate the trade area radius, then we show the cause and effect model to estimate trade area size using store causal data. Moreover, we evaluate our model and discuss how to be decided the trade area size.
Communications in Computer and Information Science, 2021
Uploads
Papers by Takashi Namatame