• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 1
  • Tagged with
  • 2
  • 2
  • 2
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
1

Rational Corporate Risk Management Policy: An Extension of Traditional Risk Management Theory to Incorporate Observed Managerial Behavior

Roselle, Russell Paul 22 May 2006 (has links)
There is qualitative and anecdotal evidence that corporate management deviates from received risk management theory. These deviations include: an overall hesitancy to accept projects with greater levels of total risk, increased return requirements compensating for firm-specific risk, employment of hedging strategies, the insuring of diversifiable risks, corporate diversification outside of the industry constraint, and the utilization of portfolio and other variance reducing methods. The literature primarily contributes these behaviors to principal/agent conflicts. Evidence from studies on these deviations support strong arguments based in resource scarcity, cost and availability of capital, employee/community stability, and the increases in bankruptcy costs that these risk management deviation are in the interest of shareholders. When considered in the context of the long-term impact on value, the observed deviations from received corporate risk management theory contribute substantively to the perpetuation of the firm as a long-term store of value. This paper supports two hypotheses: (1) the deviation from received risk management theory by corporate managers is broadly practiced, and (2) these deviations are generally in the interest of shareholders. / Master of Arts
2

Customer Acquisition Process Digitalization: A Case Study on the Use of Machine Learning in The Corporate Insurance Industry / Digitalisering av kundanskaffningsprocessen: En fallstudie om användningen av maskininlärning inom företagsförsäkringsbranschen

Larsson, Klara, Ling, Freja January 2023 (has links)
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.

Page generated in 0.0522 seconds