A Methodology of Customer Churn Prediction based on Two-Dimensional Loyalty Segmentation (이차원 고객충성도 세그먼트 기반의 고객이탈예측 방법론)
-
- Journal of Intelligence and Information Systems
- /
- v.26 no.4
- /
- pp.111-126
- /
- 2020
Most industries have recently become aware of the importance of customer lifetime value as they are exposed to a competitive environment. As a result, preventing customers from churn is becoming a more important business issue than securing new customers. This is because maintaining churn customers is far more economical than securing new customers, and in fact, the acquisition cost of new customers is known to be five to six times higher than the maintenance cost of churn customers. Also, Companies that effectively prevent customer churn and improve customer retention rates are known to have a positive effect on not only increasing the company's profitability but also improving its brand image by improving customer satisfaction. Predicting customer churn, which had been conducted as a sub-research area for CRM, has recently become more important as a big data-based performance marketing theme due to the development of business machine learning technology. Until now, research on customer churn prediction has been carried out actively in such sectors as the mobile telecommunication industry, the financial industry, the distribution industry, and the game industry, which are highly competitive and urgent to manage churn. In addition, These churn prediction studies were focused on improving the performance of the churn prediction model itself, such as simply comparing the performance of various models, exploring features that are effective in forecasting departures, or developing new ensemble techniques, and were limited in terms of practical utilization because most studies considered the entire customer group as a group and developed a predictive model. As such, the main purpose of the existing related research was to improve the performance of the predictive model itself, and there was a relatively lack of research to improve the overall customer churn prediction process. In fact, customers in the business have different behavior characteristics due to heterogeneous transaction patterns, and the resulting churn rate is different, so it is unreasonable to assume the entire customer as a single customer group. Therefore, it is desirable to segment customers according to customer classification criteria, such as loyalty, and to operate an appropriate churn prediction model individually, in order to carry out effective customer churn predictions in heterogeneous industries. Of course, in some studies, there are studies in which customers are subdivided using clustering techniques and applied a churn prediction model for individual customer groups. Although this process of predicting churn can produce better predictions than a single predict model for the entire customer population, there is still room for improvement in that clustering is a mechanical, exploratory grouping technique that calculates distances based on inputs and does not reflect the strategic intent of an entity such as loyalties. This study proposes a segment-based customer departure prediction process (CCP/2DL: Customer Churn Prediction based on Two-Dimensional Loyalty segmentation) based on two-dimensional customer loyalty, assuming that successful customer churn management can be better done through improvements in the overall process than through the performance of the model itself. CCP/2DL is a series of churn prediction processes that segment two-way, quantitative and qualitative loyalty-based customer, conduct secondary grouping of customer segments according to churn patterns, and then independently apply heterogeneous churn prediction models for each churn pattern group. Performance comparisons were performed with the most commonly applied the General churn prediction process and the Clustering-based churn prediction process to assess the relative excellence of the proposed churn prediction process. The General churn prediction process used in this study refers to the process of predicting a single group of customers simply intended to be predicted as a machine learning model, using the most commonly used churn predicting method. And the Clustering-based churn prediction process is a method of first using clustering techniques to segment customers and implement a churn prediction model for each individual group. In cooperation with a global NGO, the proposed CCP/2DL performance showed better performance than other methodologies for predicting churn. This churn prediction process is not only effective in predicting churn, but can also be a strategic basis for obtaining a variety of customer observations and carrying out other related performance marketing activities.
This paper examines the circulation and dissemination of painting during and after the nineteenth century through a case study on the One Hundred Fans paintings produced as decorative folding screens at the time. One Hundred Fans paintings refer to depictions of layers of fans in various shapes on which pictures of diverse themes are drawn. Fans and paintings on fans were depicted on paintings before the nineteenth century. However, it was in the nineteenth century that they began to be applied as subject matter for decorative paintings. Reflecting the trend of enjoying extravagant hobbies, fans and paintings on fans were mainly produced as folding screens. The folding screen of One Hundred Fans from the collection of the Museum am Rothenbaum Kulturen und Künste der Welt (hereafter Rothenbaum Museum) in Germany was first introduced to Korean in the exhibition The City in Art, Art in the City held at the National Museum of Korea in 2016. Each panel in this six-panel folding screen features more than five different fans painted with diverse topics. This folding screen is of particular significance since the National Museum of Korea holds the original drawings. In the nineteenth century, calligraphy and painting that had formerly been enjoyed by Joseon royal family members and the nobility in private spaces began to spread among common people and was distributed through markets. In accordance with the trend of adorning households, colorful decorative paintings were preferred, leading to the popularization of the production of One Hundred Fans folding screens with pictures in different shapes and themes. A majority of the Korean collection in the Rothenbaum Museum belonged to Heinrich Constantin Eduard Meyer(1841~1926), a German businessman who served as the Joseon consul general in Germany. From the late 1890s until 1905, Meyer traveled back and forth between Joseon and Germany and collected a wide range of Korean artifacts. After returning to Germany, he sequentially donated his collections, including One Hundred Fans, to the Rothenbaum Museum. Folding screens like One Hundred Fans with their fresh and decorative beauty may have attracted the attention of foreigners living in Joseon. The One Hundred Fans at the Rothenbaum Museum is an intriguing work in that during its treatment, a piece of paper with the inscription of the place name "Donghyeon" was found pasted upside down on the back of the second panel. Donghyeon was situated in between Euljiro 1-ga and Euljiro 2-ga in present-day Seoul. During the Joseon Dynasty, a domestic handicraft industry boomed in the area based on licensed shops and government offices, including the Dohwaseo (Royal Bureau of Painting), Hyeminseo (Royal Bureau of Public Dispensary), and Jangagwon (Royal Bureau of Music). In fact, in the early 1900s, shops selling calligraphy and painting existed in Donghyeon. Thus, it is very likely that the shops where Meyer purchased his collection of calligraphy and painting were located in Donghyeon. The six-panel folding screen One Hundred Fans in the collection of the Rothenbaum Museum is thought to have acquired its present form during a process of restoring Korean artifacts works in the 1980s. The original drawings of One Hundred Fans currently housed in the National Museum of Korea was acquired by the National Folk Museum of Korea between 1945 and 1950. Among the seven drawings of the painting, six indicate the order of their panels in the margins, which relates that the painting was originally an eight-panel folding screen. Each drawing shows more than five different fans. The details of these fans, including small decorations and patterns on the ribs, are realistically depicted. The names of the colors to be applied, including 'red ocher', 'red', 'ink', and 'blue', are written on most of the fans, while some are left empty or 'oil' is indicated on them. Ten fans have sketches of flowers, plants, and insects or historical figures. A comparison between these drawings and the folding screen of One Hundred Fans at the Rothenbaum Museum has revealed that their size and proportion are identical. This shows that the Rothenbaum Museum painting follows the directions set forth in the original drawings. The fans on the folding screen of One Hundred Fans at the Rothenbaum Museum are painted with images on diverse themes, including landscapes, narrative figures, birds and flowers, birds and animals, plants and insects, and fish and crabs. In particular, flowers and butterflies and fish and crabs were popular themes favored by nineteenth century Joseon painters. It is noteworthy that the folding screen One Hundred Fans at the Rothenbaum Museum includes several scenes recalling the typical painting style of Kim Hong-do, unlike other folding screens of One Hundred Fans or Various Paintings and Calligraphy. As a case in point, the theme of "Elegant Gathering in the Western Garden" is depicted in the Rothenbaum folding screen even though it is not commonly included in folding screens of One Hundred Fans or One Hundred Paintings due to spatial limitations. The scene of "Elegant Gathering in the Western Garden" in the Rothenbaum folding screen bears a resemblance to Kim Hong-do's folding screen of Elegant Gathering in the Western Garden at the National Museum of Korea in terms of its composition and style. Moreover, a few scenes on the Rothenbaum folding screen are similar to examples in the Painting Album of Byeongjin Year produced by Kim Hong-do in 1796. The painter who drew the fan paintings on the Rothenbaum folding screen is presumed to have been influenced by Kim Hong-do since the fan paintings of a landscape similar to Sainsam Rock, an Elegant Gathering in the Western Garden, and a Pair of Pheasants are all reminiscent of Kim's style. These paintings in the style of Kim Hong-do are reproduced on the fans left empty in the original drawings. The figure who produced both the original drawings and fan paintings appears to have been a professional painter influenced by Kim Hong-do. He might have appreciated Kim's Painting Album of Byeongjin Year or created duplicates of Painting Album of Byeongjin Year for circulation in the art market. We have so far identified about ten folding screens remaining with the One Hundred Fans. The composition of these folding screens are similar each other except for a slight difference in the number and proportion of the fans or reversed left and right sides of the fans. Such uniform composition can be also found in the paintings of scholar's accoutrements in the nineteenth century. This suggests that the increasing demand for calligraphy and painting in the nineteenth century led to the application of manuals for the mass production of decorative paintings. As the demand for colorful decorative folding screens with intricate designs increased from the nineteenth century, original drawings began to be used as models for producing various paintings. These were fully utilized when making large-scale folding screens with images such as Guo Ziyi's Enjoyment-of-Life Banquet, Banquet of the Queen Mother of the West, One Hundred Children, and the Sun, Cranes and Heavenly Peaches, all of which entailed complicated patterns. In fact, several designs repeatedly emerge in the extant folding screens, suggesting the use of original drawings as models. A tendency toward using original drawings as models for producing folding screens in large quantities in accordance with market demand is reflected in the production of the folding screens of One Hundred Fans filled with fans in different shapes and fan paintings on diverse themes. In the case of the folding screens of One Hundred Paintings, bordering frames are drawn first and then various paintings are executed inside the frames. In folding screens of One Hundred Fans, however, fans in diverse forms were drawn first. Accordingly, it must have been difficult to produce them in bulk. Existing examples are relatively fewer than other folding screens. As discussed above, the folding screen of One Hundred Fans at the Rothenbaum Museum and its original drawings at the National Museum of Korea aptly demonstrate the late Joseon painting trend of embracing and employing new painting styles. Further in-depth research into the Rothenbaum painting is required in that it is a rare example exhibiting the influence of Kim Hong-do compared to other paintings on the theme of One Hundred Fans whose composition and painting style are more similar to those found in the work of Bak Gi-jun.
The evolution of instant communication has mirrored the development of the Internet and messenger applications are among the most representative manifestations of instant communication technologies. In messenger applications, senders use emoticons to supplement the emotions conveyed in the text of their messages. The fact that communication via messenger applications is not face-to-face makes it difficult for senders to communicate their emotions to message recipients. Emoticons have long been used as symbols that indicate the moods of speakers. However, at present, emoticon-use is evolving into a means of conveying the psychological states of consumers who want to express individual characteristics and personality quirks while communicating their emotions to others. The fact that companies like KakaoTalk, Line, Apple, etc. have begun conducting emoticon business and sales of related content are expected to gradually increase testifies to the significance of this phenomenon. Nevertheless, despite the development of emoticons themselves and the growth of the emoticon market, no suitable emoticon recommendation system has yet been developed. Even KakaoTalk, a messenger application that commands more than 90% of domestic market share in South Korea, just grouped in to popularity, most recent, or brief category. This means consumers face the inconvenience of constantly scrolling around to locate the emoticons they want. The creation of an emoticon recommendation system would improve consumer convenience and satisfaction and increase the sales revenue of companies the sell emoticons. To recommend appropriate emoticons, it is necessary to quantify the emotions that the consumer sees and emotions. Such quantification will enable us to analyze the characteristics and emotions felt by consumers who used similar emoticons, which, in turn, will facilitate our emoticon recommendations for consumers. One way to quantify emoticons use is metadata-ization. Metadata-ization is a means of structuring or organizing unstructured and semi-structured data to extract meaning. By structuring unstructured emoticon data through metadata-ization, we can easily classify emoticons based on the emotions consumers want to express. To determine emoticons' precise emotions, we had to consider sub-detail expressions-not only the seven common emotional adjectives but also the metaphorical expressions that appear only in South Korean proved by previous studies related to emotion focusing on the emoticon's characteristics. We therefore collected the sub-detail expressions of emotion based on the "Shape", "Color" and "Adumbration". Moreover, to design a highly accurate recommendation system, we considered both emotion-technical indexes and emoticon-emotional indexes. We then identified 14 features of emoticon-technical indexes and selected 36 emotional adjectives. The 36 emotional adjectives consisted of contrasting adjectives, which we reduced to 18, and we measured the 18 emotional adjectives using 40 emoticon sets randomly selected from the top-ranked emoticons in the KakaoTalk shop. We surveyed 277 consumers in their mid-twenties who had experience purchasing emoticons; we recruited them online and asked them to evaluate five different emoticon sets. After data acquisition, we conducted a factor analysis of emoticon-emotional factors. We extracted four factors that we named "Comic", Softness", "Modernity" and "Transparency". We analyzed both the relationship between indexes and consumer attitude and the relationship between emoticon-technical indexes and emoticon-emotional factors. Through this process, we confirmed that the emoticon-technical indexes did not directly affect consumer attitudes but had a mediating effect on consumer attitudes through emoticon-emotional factors. The results of the analysis revealed the mechanism consumers use to evaluate emoticons; the results also showed that consumers' emoticon-technical indexes affected emoticon-emotional factors and that the emoticon-emotional factors affected consumer satisfaction. We therefore designed the emoticon recommendation system using only four emoticon-emotional factors; we created a recommendation method to calculate the Euclidean distance from each factors' emotion. In an attempt to increase the accuracy of the emoticon recommendation system, we compared the emotional patterns of selected emoticons with the recommended emoticons. The emotional patterns corresponded in principle. We verified the emoticon recommendation system by testing prediction accuracy; the predictions were 81.02% accurate in the first result, 76.64% accurate in the second, and 81.63% accurate in the third. This study developed a methodology that can be used in various fields academically and practically. We expect that the novel emoticon recommendation system we designed will increase emoticon sales for companies who conduct business in this domain and make consumer experiences more convenient. In addition, this study served as an important first step in the development of an intelligent emoticon recommendation system. The emotional factors proposed in this study could be collected in an emotional library that could serve as an emotion index for evaluation when new emoticons are released. Moreover, by combining the accumulated emotional library with company sales data, sales information, and consumer data, companies could develop hybrid recommendation systems that would bolster convenience for consumers and serve as intellectual assets that companies could strategically deploy.