Diploma thesis " The real role of knowledge mining " is divided into two major parts, the theoretical and the practical. The practical part describes the basic concepts of data mining, various methods and types of tasks used for knowledge discovery in databases and algorithms used in this area . Main focus is devoted to the CRISP -DM methodology and to various stages of knowledge discovery from databases. This methodology will be later used as the basis for practical part of the thesis while other less known methods used for data mining won`t be neglected. List of paid and free software which can be used for knowledge mining in databases is presented at the end of theoretical part. The second part of the thesis is focused on the practical step by step application of the CRISP -DM methodology, which contains real data from the field of mobile communications. Data mining task used in practical part is the behavioral prediction of mobile carrier customers. Supporting the practical part of the thesis, IBM SPSS Modeler was used as a main software for knowledge mining. Key words: data mining, knowledge disvocery in databases. Churm management, prediction, CRISP-DM.

Online Health Communities (OHCs) have positively disrupted the modern global healthcare system as patients and caregivers are interacting online with similar peers to improve quality of their life. Social support is the pillar of OHCs and, hence, analyzing the different types of social support activities contributes to a better understanding and prediction of future user engagement in OHCs. This thesis used data from a popular OHC, called Breastcancer.org, to first classify user posts in the community into the different categories of social support using Word2Vec for language processing and six different classifiers were explored, resulting in the conclusion that Random Forest was the best approach for classification of the user posts. This exercise helped identify the different types of social support activities that users participate in and also detect the most common type of social support activity among users in the community. Thereafter, three trajectory-based methods were proposed and implemented to predict user churn (attrition) from the OHC. Comparison of the proposed trajectory-based methods with two non-trajectory-based benchmark methods helped establish that user trajectories, which represent the month-to-month change in the type of social support activity of users are effective pointers for user churn from the community. The results and findings from this thesis could help OHC managers better understand the needs of users in the community and take necessary steps to improve user retention and community management.

One of the major challenges for modern technology companies is user retentionmanagement. This work focuses on identifying early usage patterns that signifyincreased retention rates in a mobile web browser.This is done using a targetedparallel implementation of the association rule mining algorithm FP-Growth.Different item subset selection techniques including clustering and otherstatistical methods have been used in order to reduce the mining time and allowfor lower support thresholds.A lot of interesting rules have been mined. The best retention-wise ruleimplies a retention rate of 99.5%. The majority of the rules analyzed in thiswork implies a retention rate increase between 150% and 200%.

Kundbortfall är en utmaning vilket flertalet organisationer står inför. Tidigare studier påvisar att digital marknadsföring kan vara en lösning för att minska kundbortfall, detta på grund av att digital marknadsföring kan bidra till ökad kundnöjdhet vilket i sin tur leder till kundlojalitet. Denna lojalitet gör att kunden stannar hos organisationen trots att de får erbjudanden från konkurrenter. Syftet med denna kvalitativa studie är att undersöka hur och varför digital marknadsföring nyttjas för att hämma kundbortfall inom telekommunikationsbolag. Valet av bransch och avgränsning baseras på att telekommunikationsbranschen påverkas kraftigt av kundbortfall. Detta på grund av den hårda konkurrensen samt att marknaden inom branschen är mättad. Leverantörer och konkurrenter erbjuder liknande produkter och tjänster vilket är en bidragande faktorer för kundbortfall inom telekommunikationsbranschen. Uppsatsens slutsats utformas från en analys av insamlad empiri från semistrukturerade intervjuer som analyseras med stöd av teoretiskt referensram, tidigare forskning samt bakgrund till ämnet. Resultatet tydliggör vikten av digital marknadsföring i kommunikationen för att möjliggöra lönsamhet i form av kundnöjdhet. Resultatet tydliggör även hur digital marknadsföring nyttjas i syfte att förstå kundbeteende samt ge stöd i utformningen av recovery strategies. / Organisations are facing a crucial challenge in terms of customer churn. Previous studies show that digital marketing can be a solution to reduce customer churn. This is because digital marketing can contribute to increased customer satisfaction, which in turn leads to customer loyalty. This loyalty makes the customer stay with the organisation despite receiving offers from competitors. The purpose of this qualitative research is to investigate how and why digital marketing is used to inhibit customer churn in telecommunications companies. The choice of industry and demarcation is based on the fact that the telecommunications industry is heavily affected by customer churn. This is due to the fierce competitive environment and the saturation of the market within the industry. Suppliers and competitors offer similar products and services, which is a contributing factor to customer churn in the telecommunications industry. The conclusion of this paper is formulated from an analysis of collected empirical data from semi-structured interviews which are analysed with the support of theoretical framework, previous research and background to the topic. The findings clarify the importance of digital marketing in communication to enable profitability through customer satisfaction. The study also clarifies how digital marketing is used to understand customer behaviour and to support the development of recovery strategies.

Background: Customer churn prediction is one of the most popular part of bigbusinesses and often help the companies in customer retention and revenue generation.Customer churn may lead to huge loss of revenue and is important to analyzeand determine the cause for churn. Moreover, it is easier to retain an existing customerrather than acquiring new clients.Therefore, to get a better understanding onchurn prediction, this research work focuses on finding the best performing machinelearning model after effective comparision among four machine learning models. Theresearch also gives a brief report of latest literature work done in churn analysis ofmusic streaming services. Objectives: In this thesis work, we aim to research about churn prediction done inmusic streaming services. We focus on two main objectives, first one includes literaturereview on the latest research work done in churn prediction of music streamingservices. Secondly, we aim in comparing the performance of four supervised machinelearning algorithms, to find out the best performing algorithm for churn prediction. Methods: This thesis involves two methods literature review and experimentationto answer our research questions. We chose to use literature review for RQ1 soit can give a better understanding on our selected problem and works as base workfor our research and helps in clear and better comprehension. Experimentation ischosen for RQ2 to to build and train the selected machine learning model to validatethe performance of algorithms. Experimentation is chosen because it gives betterresults and prediction compared to surveys and reviews. Results: We have selected four classification supervised machine learning algorithmsnamely, Logistic regression, Naive Bayes, KNN, and RF in this research.Upon experimentation and training the models using the algorithms with a preprocessingthe KKBox’s dataset, RF achieved highest accuracy of 97% compared toother models. Conclusions: We have trained four models using the four machine learning algorithmsfor the prediction of churn in music streaming service domain. Upon trainingthe models with the KKBox’s dataset and upon experimentation, we came to a conclusionthat RF has the best performance with better accuracy and AUC score.

Många företag drabbas regelbundet av churn, ett tillstånd som innebär att existerande kunder slutar handla hos företaget eller använda företagets tjänster för att istället vända sig till konkurrenter. För att säkerställa lojalitet bland kunderna behöver företag därför etablera metoder för att tidigt vinna kundens tillit. Med hjälp av maskininlärning kan processen att identifiera churn automatiseras, så kallad churnprediktion. Mycket forskning finns kring churnprediktion, framförallt inom telekomsektorn och inom företag som erbjuder prenumerationstjänster. Majoriteten av tidigare exempel bygger dock på kunddata som samlats in från flera tidpunkter och syftar till att predicera churn inom en längre tidsperiod, vanligtvis inom ett år. Det finns färre exempel inom kontexten e-handeln, samt forskning om hur maskininlärning kan tillämpas för att enbart utifrån data från kundens första köp och inom en kortare tidsperiod identifiera churn. I denna studie har två maskininlärningsmodeller utvecklats baserat på Random Forest-algoritmen och Logistisk Regression-algoritmen. Syftet var att undersöka vilken algoritm som är bäst lämpad för att predicera om en given kund kommer handla igen eller inte inom en tremånadersperiod, enbart med data från kundens första köp. Undersökningen baserades på data från ett svenskt e-handelsföretag. Modellerna utvärderades med mått för klassificeringsproblem, bland annat Cohen’s kappa och AUC. Trots att Logistisk regression visar sig prestera något bättre tyder resultaten på att båda modellerna har generellt svårt att avgöra om kunden kommer utsätta företaget för churn eller ej. En möjlig förklaring anses vara datamängdens restriktivitet som endast innehåller data från kundens första köp. Däremot konstateras båda modellernas möjlighet att filtrera ut kunder som löper hög risk att utsätta företaget för churn, där Random Forest visar sig vara något bättre på detta. Slutligen konstaterades att modellerna inte påvisar kraftig förbättring jämfört med en naiv lösning där alla kunder antas utsätta företaget för churn, men eftersom även små förbättringar innebär att företaget kan spara pengar kan dock modellernas användbarhet motiveras. / Companies are continuously affected by churn, a condition where existing customers turn to competitors instead using the company’s services. To ensure customer loyalty, it is vital for the company to establish methods to gain the customers trust early on. With the help of machine learning, the process for identifying churn can be automated, known as churn prediction. Research on churn prediction is abundant, especially concerning the telecom sector and subscription-based services. Most of these articles, however, are based on additional, historical data surrounding the customer, aiming to predict churn within a longer time frame, usually a year. The articles focusing on e-commerce, combined with how machine learning can be applied to identify churn within a short period, based solely on data from the customer’s first purchase, are scarce. Two machine learning models are developed based on the Random Forest-algorithm and the Logistic Regression-algorithm. These are tested to see which algorithm is best suited for predicting whether a given customer will buy again or not within a three-month period, with only data from the customer's first purchase from a Swedish e-commerce company. The models were then evaluated with classification metrics, including Cohen’s kappa and AUC. Despite the fact that Logistic Regression performed slightly better, the results showed that both models struggled with the churn prediction. A possible explanation is the restrictiveness of the data set. However, with the option of changing the calibration points on the models’ confidence, allowing the filtration of customers who have a greater chance of leading to churn, both models performed better with Random Forest being slightly superior. The models are considered a slight improvement to a naïve solution where all customers are treated as possible churn. They are also useful given the context, where even minor prevention of churn can lead to profit for the company.

Prenumerationstjänster blir alltmer populära i dagens samhälle. En av nycklarna för att lyckas med en prenumerationsbaserad affärsmodell är att minimera kundbortfall (eng. churn), dvs. kunder som avslutar sin prenumeration inom en viss tidsperiod. I och med den ökande digitaliseringen, är det nu enklare att samla in data än någonsin tidigare. Samtidigt växer maskininlärning snabbt och blir alltmer lättillgängligt, vilket möjliggör nya infallsvinklar på problemlösning. Denna rapport kommer testa och utvärdera ett försök att förutsäga kundbortfall med hjälp av maskininlärning, baserat på kunddata från ett företag med en prenumerationsbaserad affärsmodell där prenumeranten får besöka live-event till en fast månadskostnad. De maskininlärningsmodeller som användes i testerna var Random Forests, Support Vector Machines, Logistic Regression, och Neural Networks som alla tränades med användardata från företaget. Modellerna gav ett slutligt träffsäkerhetsresultat i spannet mellan 73,7 % och 76,7 %. Därutöver tenderade modellerna att ge ett högre resultat för precision och täckning gällande att klassificera kunder som sagt upp sin prenumeration än för de som fortfarande var aktiva. Dessutom kunde det konstateras att de kundegenskaper som hade störst inverkan på klassifikationen var ”Använda Biljetter” och ”Längd på Prenumeration”. Slutligen kommer det i denna rapport diskuteras hur informationen angående vilka kunder som sannolikt kommer avsluta sin prenumeration kan användas ur ett mer affärsmässigt perspektiv. / In today’s world subscription-based online services are becoming increasingly popular. One of the keys to success in a subscription-based business model is to minimize churn, i.e. customer canceling their subscriptions. Due to the digitalization of the world, data is easier to collect than ever before. At the same time machine learning is growing and is made more available. That opens up new possibilities to solve different problems with the use of machine learning. This paper will test and evaluate a machine learning approach to churn prediction, based on the user data from a company with an online subscription service letting the user attend live shows to a fixed price. To perform the tests different machine learning models were used, both individually and combined. The models were Random Forests, Support Vector Machines, Logistic Regression and Neural Networks. In order to train them a data set containing either active or churned users was provided. Eventually the models returned accuracy results ranging from 73.7 % to 76.7 % when classifying churners based on their activity data. Furthermore, the models turned out to have higher scores for precision and recall for classifying the churners than the non-churners. In addition, the features that had the most impact on the model regarding the classification were Tickets Used and Length of Subscription. Moreover, this paper will discuss how churn prediction can be used from a business perspective.

This report is about examining the fields of machine learning and digital marketing, using machine learning as a tool to predict churn in a new domain of companies that do not track their customers extensively, i.e where behaviour data is discontinuous.  To predict churn relatively simple out of the box models, such as support vector machines and random forests, are used to achieve an acceptable outcome. To be on par with the models used for churn prediction in subscription based services, this report concludes that more research has to be done using more effective evaluation metrics. Finally it is presented how these discoveries can be commercialized and the business related benefits of using churn prediction for the employer Sellpy. / Denna rapport handlar om att utforska fälten maskininlärning och digital marknadsföring, genom att använda maskininlärning som ett redskap för att förutspå churn i en typ av företag med diskontinuerlig beteendedata. För att förutspå churn finns relativt simpla "out of the box"-modeller, som support vector machines och random forests, som används för att nå acceptabla resultat. För att nå liknande resultat som i arbeten där churn utförs på kontinuerlig beteendedata konstaterar denna rapport att framtida arbeten forska på vilka utvärderingsmetriker som är mest lämpade. I rapporten presenteras också hur dessa upptäckter kan kommersialiseras och hur företaget Sellpy kan tjäna på att förutspå churn.

Le domaine de l’assurance automobile fonctionne par cycles présentant des phases de profitabilité et d’autres de non-profitabilité. Dans les phases de non-profitabilité, les compagnies d’assurance ont généralement le réflexe d’augmenter le coût des primes afin de tenter de réduire les pertes. Par contre, de très grandes augmentations peuvent avoir pour effet de massivement faire fuir la clientèle vers les compétiteurs. Un trop haut taux d’attrition pourrait avoir un effet négatif sur la profitabilité à long terme de la compagnie. Une bonne gestion des augmentations de taux se révèle donc primordiale pour une compagnie d’assurance. Ce mémoire a pour but de construire un outil de simulation de l’allure du porte- feuille d’assurance détenu par un assureur en fonction du changement de taux proposé à chacun des assurés. Une procédure utilisant des régressions à l’aide de processus gaus- siens univariés est développée. Cette procédure offre une performance supérieure à la régression logistique, le modèle généralement utilisé pour effectuer ce genre de tâche. / The field of auto insurance is working by cycles with phases of profitability and other of non-profitability. In the phases of non-profitability, insurance companies generally have the reflex to increase the cost of premiums in an attempt to reduce losses. For cons, very large increases may have the effect of massive attrition of the customers. A too high attrition rate could have a negative effect on long-term profitability of the company. Proper management of rate increases thus appears crucial to an insurance company. This thesis aims to build a simulation tool to predict the content of the insurance portfolio held by an insurer based on the rate change proposed to each insured. A proce- dure using univariate Gaussian Processes regression is developed. This procedure offers a superior performance than the logistic regression model typically used to perform such tasks.

De nos jours, les applications de grande taille sont développées à l’aide de nom- breux cadres d’applications (frameworks) et intergiciels (middleware). L’utilisation ex- cessive d’objets temporaires est un problème de performance commun à ces applications. Ce problème est appelé “object churn”. Identifier et comprendre des sources d’“object churn” est une tâche difficile et laborieuse, en dépit des récentes avancées dans les tech- niques d’analyse automatiques. Nous présentons une approche visuelle interactive conçue pour aider les développeurs à explorer rapidement et intuitivement le comportement de leurs applications afin de trouver les sources d’“object churn”. Nous avons implémenté cette technique dans Vasco, une nouvelle plate-forme flexible. Vasco se concentre sur trois principaux axes de con- ception. Premièrement, les données à visualiser sont récupérées dans les traces d’exécu- tion et analysées afin de calculer et de garder seulement celles nécessaires à la recherche des sources d’“object churn”. Ainsi, des programmes de grande taille peuvent être vi- sualisés tout en gardant une représentation claire et compréhensible. Deuxièmement, l’utilisation d’une représentation intuitive permet de minimiser l’effort cognitif requis par la tâche de visualisation. Finalement, la fluidité des transitions et interactions permet aux utilisateurs de garder des informations sur les actions accomplies. Nous démontrons l’efficacité de l’approche par l’identification de sources d’“object churn” dans trois ap- plications utilisant intensivement des cadres d’applications framework-intensive, inclu- ant un système commercial. / Nowadays, large framework-intensive programs are developed using many layers of frameworks and middleware. Bloat, and particularly object churn, is a common per- formance problem in framework-intensive applications. Object churn consists of an ex- cessive use of temporary objects. Identifying and understanding sources of churn is a difficult and labor-intensive task, despite recent advances in automated analysis tech- niques. We present an interactive visualization approach designed to help developers quickly and intuitively explore the behavior of their application with respect to object churn. We have implemented this technique in Vasco, a new flexible and scalable visualization platform. Vasco follows three main design goals. Firstly, data is collected from execu- tion traces. It is analyzed in order to calculate and keep only the data that is necessary to locate sources of object churn. Therefore, large programs can be visualized while keeping a clear and understandable view. Secondly, the use of an intuitive view allows minimizing the cognitive effort required for the visualization task. Finally, the fluidity of transitions and interactions allows users to mentally preserve the context throughout their interactions. We demonstrate the effectiveness of the approach by identifying churn in three framework-intensive applications, including a commercial system.