This thesis explores the application of machine learning 8ml9 techniques in customer classification and their intergration into customer relationship management (CRM) systems within the corporate insurance industry. The research aims to address the gap in the use of AI-CRM for the corporate insurance industry. It was conducted as a case study at a Swedish insurance broker company. The study leveraged external data sources to create a data seet on customer information. The feature selection process included Variance Influence Factor (VIF) to remove collinearity and then Mutual Class Info and Random Forest, which are methods used to find which independent variables affect the dependent variable the most. Also, Recursive Feature Testing was applied to find the best feature combinations. Four different binary classification models were implemented and compared - Decision Tree, Random Forest, Support Vector Machine, and Artificial Neural Network. Note that Random Forest can be used both for feature selection and classification. The models were tested on four different feature combinations and evaluated using Accuracy, Recall, Precision, F1-score, and ROC-AUC. The study further conducted interviews at the partner company to evaluate their current CRM system. The findings show that ML-based customer classification can be leveraged to effectivize the customer acquisition process for corporate insurance. The Support Vector Machine model achieved the highest accuracy, at 80%. Depending on the avaliable data and the use of metrics, different classifiers had the best performance. The study also found that when implementing classification into AI-CRM, the specific requirements at the company need to be examined. This study found it important to conersider the data procurement process, the current customer acquisition process, the risks associated with misclassification, and present bias. The findings of this study have theoretical implications for the implementation of AI-CRM for customer acqusition. It demonstrates the practical benefits of intergrating machine learning techniques into CRM systems, emphasizing the effectiveness of AI-CRM for customer classification. Further, by comparing different classification models and evaluating their performance, the study enhances the theoretical understanding of model selection for customer classification tasks in this specific domain. Additionally, the research provides insights into effective feature selection methods, aiding researchers and practitioners in extracting relevant variables for customer classification. / Denna studie utforskar tillämpningen av maskininlärning (ML) inom kundklassificering och dess intergration i kundrelationssystem (CRM) inom företagsförsäkringsbranschen. Forskningen syftar till att fylla kunskapsluckan inom användningen av AI-CRM inom företagsförsäkringsbranschen. Studien genomfördes som en fallstudie på ett svenskt försäkringsmäklarföretag. Studien utnyttjade externa datakällor för att skapa en dataset av kundinformation. Processen för val av variabler inkluderade Variance Influence Factor (VIF) för att ta bort kollinearitet och sedan Mutual Class Info och Random Forest, som är metoder som användsför att hitta vilka oberoende variabler som påverkar den beroende variabeln mest. Dessutom användes Recursive Feature Testing för att hitta de bästa kombinationerna av funktioner. Fyra olika binära klassificeringsmodeller implementerades och jämfördes- Decision Tree, Random Forest, Support Vector Machine och Artificial Neural Network. Observera att Random Forest kan användas både för val av funktioner och klassificering. Modellerna testades med fyra olika kombinationer av variabler och utvärderades med hjälp av Accuracy Recall, Precision, F1-score och ROC-AUC. Studien genomförde även intervjuer på partnerföretaget för att utvärdera deras nuvarande CRM-system. Resultaten visar att ML-baserad kundklassificering kan användas för att effektivisera processen för kundanskaffning inom företagsförsäkring.  Support Vector Machine-modellen uppnådde högst accuracy, 80%. Beroende på tillgängliga data och användning av evalueringsmått hade olika klassificerade bäst prestanda. Studien fann också att vid implementering av klassificering i AI-CRM måste de specifika kraven på företaget undersökas. Denna studie fann det viktigt att beakta processen för dataanskaffning, den nuvarande processen för kundanskaffning, riskerna med felklassificering och nuvarande partiskhet. Resultaten av denna studie har teoretiska implikationer för implementeringen av AI-CRM för kundanskaffning. Den visar på de praktiska fördelarna med att integrera maskininlärningstekniker i CRM-system och betonar effektiviteten hos AI-CRM för kundklassificering. Dessutom förbättrar studien den teoretiska förståelsen för val av modeller för kundklassificeringsuppgifter i det specifika domänet genom att jämföra olika klassificeringsmodeller och utvärdera deras prestanda. Studien ger också insikter om effektiva metoder för val av variabler och hjälper forskare och utövare att extrahera relevanta variabler för kundklassificering.

SAMMANFATTNING  Datum: 2022-01-13 Nivå: Kandidatuppsats i företagsekonomi, 15 hp  Institution: Akademin för Ekonomi, Samhälle och Teknik, Mälardalens universitet Författare: Dolshi Hayllie  Ranim, Mashhadi  Mohammed Salman  (000517) (920627) (960229) Titel: Kundlojalitet ur kundens perspektiv Handledare: Ulf Andersson Nyckelord: CRM, engagemang, word of mouth, kundlojalitet, förtroende, relation Frågeställning: Vilka faktorer påverkar lojalitet hos digitala klädföretag ur kundens perspektiv? Syfte: Syftet med denna studie är att öka kunskapen kring kundlojalitet och undersöka vilka faktorer som kan påverka lojalitet. Syftet är också att skapa förståelse kring hur CRM kan påverka kunders lojalitet i digitala klädföretag. Metod: Denna studie är baserad på en kvalitativ metod. Insamling av primärdata kommer att tas via en strukturerad intervju hos två fokusgrupper. Kvalitativ metod valdes då den lägger vikt på ord vid datainsamling snarare än kvantifiering. Syftet med uppsatsen är att studera dessa faktorer som kan påverka kunders lojalitet i digitala klädföretag, har det valts att använda en kvalitativ metod. Studien utgår från det deduktiva synsättet för att redogöra förhållandet mellan teori och forskning. Slutsats: Studien visade att flera faktorer har bidragit till en ökad kundlojalitet och att CRM är ett effektivt sätt för att hantera sina kundrelationer. Engagemang, förtroende och relation har visat sig vara de mest centrala faktorerna samt att CRM bör nyttjas hos alla företag Digitala klädföretag har sina utmaningar med att upprätthålla kundrelationer och att ett digitalt CRM förenklar processen och gör det möjligt att ta reda på hur man skapar, värvar och behåller kunder i längden.

For companies that supply a service to their customers, there will always be a difference in engagement from customer to customer. Some customers might have created an account, they might also have a paid subscription, or they neither have an account nor are a subscriber. Meaning that they only interact with the free content provided. Looking at this from the perspective of the company, a more engaged customer will generate more value than one less engaged. Therefore, it would be beneficial to try and understand why some customers are more engaged than others. This project purpose is to create a customer relationship management (CRM) pipeline for determining what it is that make some users more engaged with a service than other. The findings will be presented to Bonnier that they may use to try and increase customer engagement across the board. This is achieved by clustering users based on their recency, frequency, and volume (RFV) data with the help of two clustering algorithms. The clustering algorithms are evaluated to detriment which is more suited as well as to determine the optimal number of clusters. Lastly the clusters are analysed on different metrics connected to the users as well as to the articles they read. The results show some implications into what makes some users more engaged. It’s also concluded that more clustering and analysis would be needed to get even more insight into what leads to more customer engagement.

No description available.

Little et al., (1971) define citizen feedback as information from citizens directed to societal institutions, particularly government, to improve their functioning. Citizen feedback can further be categorized into service feedback, which includes inquiries, requests, complaints, and involvement feedback, which includes opinions, suggestions, and volunteering. There is a great dissonance between the amount of service feedback available to government organizations and its use in development and improvement of public services and policies. There is literature available that suggests governments use of social media for collecting citizen feedback. But very little research has been done to study that government organizations analyze direct communication to collect citizen feedback and what ICT tools they use or would like to use. This becomes even more relevant in countries with high eGovernment maturity with more availability of service feedback through a combination of traditional and newer channels. Therefore, this study investigates the above-mentioned research problem by answering the following two related research questions: 1) How do Swedish public organizations gather and utilize the wealth of information about citizens' needs available in the direct communication from citizens to public organizations? A) is the content of the direct communication between citizens and public organizations actionable? B) And is the volume of the communication sufficient to make it actionable 2) What kind of ICT tool support the public organizations would like to have in order to better utilize the aforementioned information? For the study, semi-structured interviews were conducted with six public officers from Swedish public organizations. The respondents were individuals working within customer relations departments of public organizations in Sweden. The respondents were not only involved in the registration, collection, analysis, and resolution of customer inquiries but also in improvement of processes and services. The interviews were conducted in Swedish, recorded and transcribed, and the transcripts were translated into English. The transcripts were then analyzed in the form of a thematic analysis following the principles of Braun & Clarke (2006). The analysis led to the discovery of five themes namely 1) Types of inquiries 2) Frequent inquiries 3) Contact channels 4) Utilization of direct communication 5) ICT tool support The study highlights the various ways in which Swedish public organizations gather and utilize service feedback. In the gathering phase, multiple channels are offered to citizens. The use of traditional channels remain high for the problem area of information supply. In the utilization phase, various strategies are used depending on eGovernment maturity. Every public organization is required to maintain a “diarium” because of laws on record keeping for transparency purposes, it is a common tool for registering citizen inquiries, and also a source for annual performance and quality reporting. Additionally, LIME CRM system is used by some organizations, citizen opinions received through webforms is analysed, phone calls recorded and analysed. Lack of alignment is a challenge for some public organizations. There is little evidence to suggest that data from various sources is integrated into a centralized CRM system, leading to insight into citizen preferences, behavior or trends.

In 2010 the United Arab Emirates (UAE) government set out to improve customer service by adopting the Customer Relationship Management (CRM) system that was used mainly in private sector. There was a concern about implementing the one size fits all CRM. Therefore, public managers needed to understand the various public sector relationship types and to consider a relational, emotional and behavioral approach to the public-government relationship rather than the technical business management approach. The research here identifies some key distinctive typologies and key contextual relationship factors to better design a management approach that suits each typology. Some key relationship components are stakeholders, services, government role, service concept and relationship exchange. Reviewing the literature from the relationship lens, many studies have focused on understanding the components of a public-government relationship. The gap in the literature highlights the need for CRM models for the government sector functions, identifying the various contextual factors of the relationship, and a need to cater to the behavioral and emotional aspect of the relationship. The seven public-government relationship typology framework emerged from meta-synthesis of the literature review. The study uses UAE Federal government CRM, specifically the Ministry of Health and Prevention (MOHAP). Grounded theory methodology was used to explore the seven public-government factors. Twenty-four qualitative interviews were conducted. The examined relationships include: entrepreneurial, public beneficiary, social beneficiary, organizer, protector, arbitrator, and supporter. The findings aid practitioners in designing the public-government relationship management approach that suits the nature of each relationship and its context. Theoretically, the relationship is the new lens for improving customer service in the public sector and the private sector. This emphasizes that the one size fits all CRM approach needs to be changed to more of a human and personalized approach to managing relationship typologies that are altered based upon context, influential components, and key factors. Some of the key factors influencing the relationships are communication, awareness, knowledge, emotional handling, engagement, relational approach, trust, and relationship value chain. This study provides good evidence for the need for further exploration of the contextual angle of relationships in the private sector in similar relationship typologies. / Ph. D.

Yes / People worldwide are largely engaged and attached with the web 2.0 technology and Social media platforms. By the same token, businesses start looking at such technologies as effective mechanisms to interact more with their customers. Equally, the related issues of social media marketing have been also the focus of attention for academics and researchers to expand the current understanding about such phenomena over the marketing area. Accordingly, the main aim of this study is to systematically examine and review the current studies that have conducted over the related area of social media and marketing. By reviewing approximately 144 articles, the researchers were able to provide an overview of the main themes and trends covered by the relevant literature such as the role of social media on advertising, the electronic word of mouth, customers’ relationship management, and firms’ brands and performance. In this review, it has also studied the most common research approaches adopted to examine the related issues of social media marketing. Further discussion is also introduced followed by an explanation of the current review limitations and recommended directions to be examined by future studies.

Purpose: The purpose of this paper is to create an understanding of how customer engagement, communication / interaction and customer insight are driving forces behind the use of Social CRM from a leadership perspective. Method: The purpose of the study, we believed it was appropriate to use a qualitative approach to conduct the study. The empirical data were collected through semi-structured interviews. The sample consisted of 10 companies located in the Gävle area who are active on social media. The interviews were coded to obtain keywords and patterns. These patterns and keywords are then analyzed to arrive at the study's results. Results and contributions: Our results suggest that all the identified benefits, customer engagement, customer insight and communication are driving forces to make use of social CRM. However, they are used to different extents with different purposes. The two main drivers are customer engagement and communication. Customer insight is the driving force that is used least extensively and least consciously. Our investigation has confirmed much of the already existing research in this area but also highlighted that all driving forces do not have the same priority. Our study contributes to a better understanding of the driving forces behind the use of social CRM.

As ferramentas visuais tem se mostrado eficazes no ensino de química. Essas ferramentas apresentam bases efetivas para a compreensão da química em seus três modos de representação (macroscópico, submicroscópico e simbólico). Apesar da importância da utilização destas ferramentas, muitos professores não estão preparados para sua utilização em sala de aula. Diante disso, surge a necessidade de formar professores com capacidades para criar metodologias que abordem as ferramentas visuais, pois estas podem facilitar o desenvolvimento da habilidade de interpretação de representações pelos estudantes. Esta pesquisa possui o objetivo de investigar se os bolsistas PIBID de química da USP, após atividades formativas, apresentaram em suas produções didáticas atividades que possuam indícios dos fatores que remetem ao desenvolvimento da habilidade representacional e se estas produções apresentam uma elevada exigência conceitual. A coleta de dados foi realizada por um acompanhamento da formação inicial a qual os bolsistas PIBID participaram. Após a formação os bolsistas acompanharam as aulas de química de uma escola da cidade de São Paulo. Durante este período os bolsistas planejaram aulas a serem aplicadas na escola. Ao final de todo o processo, os bolsistas PIBID redigiram um relatório contendo o que foi abordado, suas observações e avaliações das aulas. A análise do desenvolvimento da habilidade de interpretação de representações foi realizada através de uma metodologia qualitativa, na qual foram utilizados trechos dos relatórios que se enquadrassem ao modelo CRM, adaptado de Schonborn e Anderson (2009). Como foi observado que os bolsistas PIBID utilizaram diversos dos fatores do modelo CRM em suas produções didáticas, foi realizada uma análise para averiguar se estas produções também continham elevada exigência conceitual. O cálculo do nível de exigência conceitual foi realizado abordando uma metodologia mista, que envolve o método quantitativo e qualitativo. O cálculo mostrou que os relatórios apresentaram satisfatório nível de exigência conceitual. Com a análise foi possível concluir que esta pesquisa pode contribuir para a reflexão sobre a importância da formação de professores para o ensino de química/ciências, e ainda traz um modelo que pode servir como embasamento para que professores planejem suas aulas do modo a abordar a habilidade de interpretação de representações, que é fundamental para compreensão da química pelos estudantes. / Visual tools have been proven be very important in teaching chemistry. These tools are effective to support the understanding of chemistry in the three modes of representation (macroscopic, submicroscopic and symbolic). Despite the importance of these tools, many teachers are not prepared to use them in classrooms. This arises the need of training teachers with skills to create methodologies using visual tools, since these methodologies can facilitate the students to develop abilities to interpret representations. This research aims to investigate if after training activities, the USP chemistry students of PIBID present in their didactic productions activities evidencing the development of representational ability and a high conceptual demand. The data collection was conducted by a follow up of the initial training with scholarship students of PIBID. After the training the students participated of chemistry classes at a school in the city of São Paulo. Those classes were sometimes planned by the PIBID students. At the end of the process the PIBID students wrote a report containing what was covered, their observations and evaluations. The analysis of the development of the interpreting representations ability was realized using a qualitative methodology, in which was used parts of the report that fits the CRM model, adapted from Schonborn and Anderson (2009). Since it was observed that PIBID students used several of the CRM model factors in their didactic productions, an analysis was realized to determine whether these productions also contained evidence of high conceptual demand. The calculation of the conceptual requirement level was done by a mixed methodology, involving the quantitative and qualitative method. The calculation showed that the reports had a satisfactory conceptual requirement level. We concluded that the CRM model can be used as foundation for teachers to plan their lessons in order to develop the ability to interpretation of external representations which is fundamental to understanding the chemistry by students. We also concluded that despite the use of the CRM model factors, it is necessary that the activities elaborated by the teachers had a high conceptual demand level.

O marketing relacional tem se apresentado como uma alternativa muito promissora para empresas de diversos setores, pois desenvolve chances maiores de fidelização de clientes e promove a competitividade das organizações envolvidas. Apesar dessas vantagens, a maioria dos estudos encontrados sobre o tema, principalmente no setor do agronegócio e para mercados B2B, não se aprofundou na parte operacional de um relacionamento: as práticas e atividades. Com o intuito de explorar essa lacuna na literatura, o trabalho teve como objetivo identificar as práticas mais utilizadas pelos fornecedores e mais valorizadas pelos distribuidores de defensivos agrícolas em seus relacionamentos. Foi realizada uma pesquisa quantitativa por meio da aplicação de questionários com canais de distribuição de defensivos agrícolas. Esses questionários continham diversas práticas de relacionamento identificadas na literatura, variáveis de satisfação e caracterização das revendas. As práticas mais utilizadas e mais bem avaliadas são provenientes dos fatores comunicação, especificação dos papéis e motivação dos funcionários; por outro lado, as que apresentaram baixas taxas de utilização e de valorização foram a de laços, monitoramento e planejamento. A satisfação com os relacionamentos na amostra é afetada positivamente pelos fatores alinhamento, comunicação, especificação dos papéis e monitoramento. Também foram encontradas outras correlações com a satisfação e o tempo de duração do relacionamento. Concluiu-se que os relacionamentos nesse setor ainda são muito focados e concentrados nas vendas, mediante práticas e programas que estimulam resultados de vendas para os agricultores. Basicamente, dois grupos de práticas foram identificados: um em que as práticas são bastante usadas e valorizadas e, trazem satisfação; e as que não são tão usadas e valorizadas, porém aumentam o grau de fidelidade dos distribuidores e são fontes de poder e controle do fabricante. / Relational marketing has emerged as a very interesting alternative for companies from various industries because as it is more likely to develop customer loyalty and promote the competitiveness of the organizations involved. Nevertheless, most studies found on the subject, particularly in agribusiness and the B2B markets have not deepened on the operationalization of relationships: activities and practices. In order to exploit this gap in the literature, the study aimed to identify practices most used by suppliers and more valued by distributors of agrichemicals in their relationships. A quantitative survey was conducted through questionnaires with distribution channels for crop protection. These questionnaires contained several relationship practices identified in the literature, satisfaction variables and characterization of dealers. The most used and best evaluated practices were from the factors communication, role specifications and motivation of employees, on the other hand the ones with low utilization rates and poorest evaluations were the bonds, monitoring and planning. Satisfaction with relationships in the sample is positively affected by the factors alignment, communication, role specification and monitoring. Other correlations with the satisfaction and the time duration of the relationship were also found. It was concluded that relationships in this sector are still very focused and concentrated on sales, through practices and programs that stimulate sales results for farmers. Basically, two groups of practices were identified: one in which the practices are quite used and valued, and bring satisfaction; and those who are not as used and valued, but increases the degree of loyalty of distributors and are sources of power and control to the manufacturers.