Risk prediction in life insurance industry using supervised learning algorithms

Multi-criteria decision-making methods applied in health-insurance underwriting

This study attempts to structure methodologically the health insurance underwriting process by applying Multi-criteria Decision-making (MCDM) analysis in health insurance underwriting. This is done by assigning a score to each health insurance applicant which can be used to determine whether he or she is accepted, rejected or accepted with special terms and conditions (such as exclusions, additional waiting periods and/ or surcharge). The introduction of MCDM approaches in health insurance underwriting enables the quantification of the selection criteria, the increased standardization and automation of the process and its alignment through quantitative indicators with the risk tolerance/ risk appetite of the insurer, and there lie the novelties of this research. The proposed methodology can be readily implemented by insurers with added value in the underwriting, risk management and distribution (sales & marketing) functions, as well as in the profitability of the company or the level of premium paid by the insured.

Machine Learning-Based Regression Framework to Predict Health Insurance Premiums

Artificial intelligence (AI) and machine learning (ML) in healthcare are approaches to make people’s lives easier by anticipating and diagnosing diseases more swiftly than most medical experts. There is a direct link between the insurer and the policyholder when the distance between an insurance business and the consumer is reduced to zero with the use of technology, especially digital health insurance. In comparison with traditional insurance, AI and machine learning have altered the way insurers create health insurance policies and helped consumers receive services faster. Insurance businesses use ML to provide clients with accurate, quick, and efficient health insurance coverage. This research trained and evaluated an artificial intelligence network-based regression-based model to predict health insurance premiums. The authors predicted the health insurance cost incurred by individuals on the basis of their features. On the basis of various parameters, such as age, gender, body mass index, number of children, smoking habits, and geolocation, an artificial neural network model was trained and evaluated. The experimental results displayed an accuracy of 92.72%, and the authors analyzed the model’s performance using key performance metrics.

An interpretable prediction method for university student academic crisis warning

Data-driven techniques improve the quality of talent training comprehensively for university by discovering potential academic problems and proposing solutions. We propose an interpretable prediction method for university student academic crisis warning, which consists of K-prototype-based student portrait construction and Catboost–SHAP-based academic achievement prediction. The academic crisis warning experiment is carried out on desensitization multi-source student data of a university. The experimental results show that the proposed method has significant advantages over common machine learning algorithms. In terms of achievement prediction, mean square error (MSE) reaches 24.976, mean absolute error (MAE) reaches 3.551, coefficient of determination ($$R^{2}$$ R 2 ) reaches 80.3%. The student portrait and Catboost–SHAP method are used for visual analysis of the academic achievement factors, which provide intuitive decision support and guidance assistance for education administrators.

Predicting mortality and hospitalization in heart failure using machine learning: A systematic literature review

Objective

The partnership between humans and machines can enhance clinical decisions accuracy, leading to improved patient outcomes. Despite this, the application of machine learning techniques in the healthcare sector, particularly in guiding heart failure patient management, remains unpopular. This systematic review aims to identify factors restricting the integration of machine learning derived risk scores into clinical practice when treating adults with acute and chronic heart failure.

Methods

Four academic research databases and Google Scholar were searched to identify original research studies where heart failure patient data was used to build models predicting all-cause mortality, cardiac death, all-cause and heart failure-related hospitalization.

Results

Thirty studies met the inclusion criteria. The selected studies' sample size ranged between 71 and 716 790 patients, and the median age was 72.1 (interquartile range: 61.1–76.8) years. The minimum and maximum area under the receiver operating characteristic curve (AUC) for models predicting mortality were 0.48 and 0.92, respectively. Models predicting hospitalization had an AUC of 0.47 to 0.84. Nineteen studies (63%) used logistic regression, 53% random forests, and 37% of studies used decision trees to build predictive models. None of the models were built or externally validated using data originating from Africa or the Middle-East.

Conclusions

The variation in the aetiologies of heart failure, limited access to structured health data, distrust in machine learning techniques among clinicians and the modest accuracy of existing predictive models are some of the factors precluding the widespread use of machine learning derived risk calculators.

Product-harm crisis intelligent warning system design based on fine-grained sentiment analysis of automobile complaints

Due to the huge losses caused by product-harm crises and subsequent recalls in the automobile industry, companies must urgently design a product-harm crisis warning system. However, the designs of existing warning systems use the recurrent neural network algorithm, which suffers from gradient disappearance and gradient explosion issues. To compensate for these defects, this study uses a long and short-term memory algorithm to achieve a final prediction accuracy of 90%. This study contributes to the research and design of automatic crisis warning systems by considering sentiment and improving the accuracy of automobile product-harm crisis prediction.

A holistic FMEA approach by fuzzy-based Bayesian network and best–worst method

Failure mode and effect analysis (FMEA) is a risk analysis tool widely used in the manufacturing industry. However, traditional FMEA has limitations such as the inability to deal with uncertain failure data including subjective evaluations of experts, the absence of weight values of risk parameters, and not considering the conditionality between failure events. In this paper, we propose a holistic FMEA to overcome these limitations. The proposed approach uses the fuzzy best–worst (FBWM) method in weighting three risk parameters of FMEA, which are severity (S), occurrence (O), and detection (D), and to find the preference values of the failure modes according to parameters S and D. On the other side, it uses the fuzzy Bayesian network (FBN) to determine occurrence probabilities of the failure modes. Experts use a procedure using linguistic variables whose corresponding values are expressed in trapezoidal fuzzy numbers, and determine the preference values of the failure modes according to parameter O in the constructed BN. Thus, the FBN including expert judgments and fuzzy set theory addresses uncertainty in failure data and includes a robust probabilistic risk analysis logic to capture the dependence between failure events. As a demonstration of the approach, a case study was conducted in an industrial kitchen equipment manufacturing facility. The results of the approach have also been compared with existed methods demonstrating its robustness.

Big Data and Actuarial Science

This article investigates the impact of big data on the actuarial sector. The growing fields of applications of data analytics and data mining raise the ability for insurance companies to conduct more accurate policy pricing by incorporating a broader variety of data due to increased data availability. The analyzed areas of this paper span from automobile insurance policy pricing, mortality and healthcare modeling to estimation of harvest-, climate- and cyber risk as well as assessment of catastrophe risk such as storms, hurricanes, tornadoes, geomagnetic events, earthquakes, floods, and fires. We evaluate the current use of big data in these contexts and how the utilization of data analytics and data mining contribute to the prediction capabilities and accuracy of policy premium pricing of insurance companies. We find a high penetration of insurance policy pricing in almost all actuarial fields except in the modeling and pricing of cyber security risk due to lack of data in this area and prevailing data asymmetries, for which we identify the application of artificial intelligence, in particular machine learning techniques, as a possible solution to improve policy pricing accuracy and results.