• 한국품질경영학회:학술대회논문집
• /
• 한국품질경영학회 2004년도 품질경영모델을 통한 가치 창출
• /
• pp.573-575
• /
• 2004

This study presents a new customer segmentation method based on features that can predict the customer's buying behavior. In this method, we consider all variables that can affect the customer's buying behavior including demographics, psychographics, technographics, transaction pattern-related variables, etc. We define several features which are the combination of variables with the interaction effect by using C5.0, use SOM (Self-Organizing Map) neural networks in odor to extract the feature's patterns and classify, and then make features' rules using C5.0 far the prediction of customer buying behavior

• 한국경영과학회지
• /
• 제39권3호
• /
• pp.63-82
• /
• 2014

The main objective of this research is to investigate whether the RFM (recency-frequency-monetary value) information of a customer's redemption behavior of loyalty points can improve the prediction of future value of the customer. The conventional measurement of customer value has been primarily based on purchase transactions behavior although a customer's future behavior can be also influenced by other interactions between the customer and the firm such as redemption of rewards in a loyalty program. We theorize why a customer's redemption behavior can influence her future purchases and thereby the customer's total value based on operant learning theory, goal gradient hypothesis, and lock-in effect. Using a dataset from a major book store in Korea spanning three years between 2008 and 2010, we analyze both purchase transactions and redemption records of over 10,000 customers. The results show that the redemption-based RFM information does improve the prediction accuracy of the customer's future purchases. Based on this result, we also propose an improved estimate of customer lifetime value (CLV) by combining purchase transactions and loyalty points redemption data. Managerial implications will be also discussed for firms managing loyalty programs to maximize the total value customers.

• 응용통계연구
• /
• 제32권3호
• /
• pp.391-404
• /
• 2019

그동안의 고객 행동에 대한 예측은 주로 고객이 가지는 고정적인 특성을 이용해왔다. 최근에는 점차 고객들의 활동이 오프라인에서 온라인으로 이동하면서 각 고객의 웹 로그를 추적하는 일이 가능해졌다. 그러나 방대한 양의 웹 로그 데이터를 수집할 수 있게 된 반면, 이에 대한 연구는 로그 데이터를 정리하거나 기술적인 특성만을 설명하는 것에 그쳤다. 본 연구에서는 웹사이트 Kaggle에서 제공하는 Airbnb 고객들의 성별, 연령 등의 기본 정보 및 웹 로그가 포함된 데이터셋을 이용하여 첫 숙소 예약까지 걸리는 개인의 의사 결정 시간을 예측하였다. Lasso, SVM, Random Forest, XGBoost 등 다양한 방법론을 활용하여 최적의 모형을 찾고, 웹 로그 데이터의 유무에 따른 예측 오차를 비교하여 웹 로그의 효용성을 확인하였다. 결과적으로 오분류율이 약 20%로 낮은 랜덤 포레스트 분류모형을 최적모형으로 선택하였다. 또한, 웹 로그 데이터를 이용하여 고객 개개인의 행동을 예측한 결과 사용하지 않은 경우와 비교해 예측의 정확도가 최대 두 배 더 높아진 것을 확인할 수 있었다.

• 경영과학
• /
• 제20권2호
• /
• pp.135-149
• /
• 2003

Developing a proper program for customer evaluation is one of the most imminent tasks to implement CRM (Customer Relationship Management). Design of the Customer Value model is an important key to the customer evaluation progrgm. This paper proposes two models for estimating Customer Value. The first one is a Description Model for Customer Value based on customer CSI (Customer Satisfaction Index) data. This model represents as quantitative numbers what customers feel from the company or the service. The second one is a Prediction Model which employs factor analysis and regression to predict customer value. This paper exploits the two models to evaluate Customer Value as well as for customer behavior prediction.

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 2002년도 춘계공동학술대회
• /
• pp.306-311
• /
• 2002

This paper propose a personalized defection detection and prevention procedure based on the observation that potential defectors have tendency to take a couple of months or weeks. For this purpose, possible states of customer behavior are determined from past behavior data using SOM (Self-Organizing Map). For the evaluation of the proposed procedure, a case study has been conducted for a Korean online game site. The result demonstestes that the proposed procedure can assist defection prevention effectively and detect potential defectors without deterioration of prediction accuracy comparison to prediction by MLP. Our procedure can be applied to various service industries that can capture fluent customer behavior data such as telecommunications, internet access services, and content services, too.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2002년도 추계정기학술대회
• /
• pp.445-453
• /
• 2002

Past and current customer behavior is the best predicator of future customer behavior. This paper introduces a procedure on personalized defection detection and prevention for an online game site. The basic idea for our defection detection and prevention is adopted from the observation that potential defectors have a tendency to take a couple of months or weeks to gradually change their behavior (i.e. trim-out their usage volume) before their eventual withdrawal. For this purpose, we suggest a SOM (Self-Organizing Map) based procedure to determine the possible states of customer behavior from past behavior data. Based on this representation of the state of behavior, potential defectors are detected by comparing their monitored trajectories of behavior states with frequent and confident trajectories of past defectors. The key feature of this study includes a defection prevention procedure which recommends the desirable behavior state for the ext period so as to lower the likelihood of defection. The defection prevention procedure can be used to design a marketing campaign on an individual basis because it provides desirable behavior patterns for the next period. The experiments demonstrate that our approach is effective for defection prevention and efficient for defection detection because it predicts potential defectors without deterioration of prediction accuracy compared to that of the MLP (Multi-Layer Perceptron) neural network.

• 경영과학
• /
• 제21권3호
• /
• pp.55-69
• /
• 2004

This study analyzes customer buying-behavior patterns in a department store as time goes on, and predicts moving patterns of its customers. Through them, it suggests in this paper short-term and long-term marketing promotion strategies. RFM techniques are utilized for customer segmentation. Customers are clustered by using the Kohonen's Self Organizing Map as a method of data mining techniques. Then C5.0, a decision tree analysis technique, is used to predict moving patterns of customers. Using real world data, this study evaluates the prediction accuracy of predictive models.

• 한국산학기술학회:학술대회논문집
• /
• 한국산학기술학회 2003년도 Proceeding
• /
• pp.141-148
• /
• 2003

Customer retention is a common concern for many industries and a critical issue for the survival in today's greatly compressed marketplace. Current customer retention models only focus on detection of potential defectors based on the likelihood of defection by using demographic and customer profile information. In this paper, we propose a dynamic procedure for defection detection and prevention using past and current customer behavior by utilizing SOM and Markov chain. The basic idea originates from the observation that a customer has a tendency to change his behavior (i.e. trim-out his usage volumes) before his eventual withdrawal. This gradual pulling out process offers the company the opportunity to detect the defection signals. With this approach, we have two significant benefits compared with existing defection detection studies. First, our procedure can predict when the potential defectors could withdraw and this feature helps to give marketing managers ample lead-time for preparing defection prevention plans. The second benefit is that our approach can provide a procedure for not only defection detection but also defection prevention, which could suggest the desirable behavior state for the next period so as to lower the likelihood of defection. We applied our dynamic procedure for defection detection and prevention to the online gaming industry. Our suggested procedure could predict potential defectors without deterioration of prediction accuracy compared to that of the MLP neural network and DT.

• 지능정보연구
• /
• 제26권4호
• /
• pp.111-126
• /
• 2020

CRM의 하위 연구 분야로 진행되었던 고객이탈예측은 최근 비즈니스 머신러닝 기술의 발전으로 인해 빅데이터 기반의 퍼포먼스 마케팅 주제로 더욱 그 중요도가 높아지고 있다. 그러나, 기존의 관련 연구는 예측 모형 자체의 성능을 개선시키는 것이 주요 목적이었으며, 전체적인 고객이탈예측 프로세스를 개선하고자 하는 연구는 상대적으로 부족했다. 본 연구는 성공적인 고객이탈관리가 모형 자체의 성능보다는 전체 프로세스의 개선을 통해 더 잘 이루어질 수 있다는 가정하에, 이차원 고객충성도 세그먼트 기반의 고객이탈예측 프로세스 (CCP/2DL: Customer Churn Prediction based on Two-Dimensional Loyalty segmentation)를 제안한다. CCP/2DL은 양방향, 즉 양적 및 질적 로열티 기반의 고객세분화를 시행하고, 고객세그먼트들을 이탈패턴에 따라 2차 그룹핑을 실시한 뒤, 이탈패턴 그룹별 이질적인 이탈예측 모형을 독립적으로 적용하는 일련의 이탈예측 프로세스이다. 제안한 이탈예측 프로세스의 상대적 우수성을 평가하기 위해 기존의 범용이탈예측 프로세스와 클러스터링 기반 이탈예측 프로세스와의 성능 비교를 수행하였다. 글로벌 NGO 단체인 A사의 협력으로 후원자 데이터를 활용한 분석과 검증을 수행했으며, 제안한 CCP/2DL의 성능이 다른 이탈예측 방법론보다 우수한 성능을 보이는 것으로 나타났다. 이러한 이탈예측 프로세스는 이탈예측에도 효과적일 뿐만 아니라, 다양한 고객통찰력을 확보하고, 관련된 다른 퍼포먼스 마케팅 활동을 수행할 수 있는 전략적 기반이 될 수 있다는 점에서 연구의 의의를 찾을 수 있다.

• Asia pacific journal of information systems
• /
• 제33권3호
• /
• pp.737-767
• /
• 2023

With the availability of big customer data and advances in machine learning techniques, the prediction of customer behavior at the session-level has attracted considerable attention from marketing practitioners and scholars. This study aims to predict customer purchase conversion at the session-level by employing customer profile, transaction, and clickstream data. For this purpose, we develop a multimodal deep learning fusion model with dynamic and static features (i.e., DS-fusion). Specifically, we base page views within focal visist and recency, frequency, monetary value, and clumpiness (RFMC) for dynamic and static features, respectively, to comprehensively capture customer characteristics for buying behaviors. Our model with deep learning architectures combines these features for conversion prediction. We validate the proposed model using real-world e-commerce data. The experimental results reveal that our model outperforms unimodal classifiers with each feature and the classical machine learning models with dynamic and static features, including random forest and logistic regression. In this regard, this study sheds light on the promise of the machine learning approach with the complementary method for different modalities in predicting customer behaviors.