IMPROVING AUTOMOBILE INSURANCE CLAIMS FREQUENCY PREDICTION WITH TELEMATICS CAR DRIVING DATA

Abstract Novel navigation applications provide a driving behavior score for each finished trip to promote safe driving, which is mainly based on experts’ domain knowledge. In this paper, with automobile insurance claims data and associated telematics car driving data, we propose a supervised driving risk scoring neural network model. This one-dimensional convolutional neural network takes time series of individual car driving trips as input and returns a risk score in the unit range of (0,1). By incorporating credibility average risk score of each driver, the classical Poisson generalized linear model for automobile insurance claims frequency prediction can be improved significantly. Hence, compared with non-telematics-based insurers, telematics-based insurers can discover more heterogeneity in their portfolio and attract safer drivers with premiums discounts.

Download Full-text

Automobile Fatal Accident and Insurance Claim Analysis Through Artificial Neural Network

10.4018/978-1-7998-8455-2.ch009 ◽

2022 ◽

pp. 233-262

Author(s):

Xiangming Liu ◽

Gao Niu

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Model Comparison ◽

Claims Data ◽

Descriptive Analysis ◽

Insurance Claims ◽

Fatal Accident ◽

Insurance Claims Data ◽

Artificial Neural ◽

Artificial Neural Network Ann

This chapter presents a thorough descriptive analysis of automobile fatal accident and insurance claims data. Major components of the artificial neural network (ANN) are discussed, and parameters are investigated and carefully selected to ensure an efficient model construction. A prediction model is constructed through ANN as well as generalized linear model (GLM) for model comparison purposes. The authors conclude that ANN performs better than GLM in predicting data for automobile fatalities data but does not outperform for the insurance claims data because automobile fatalities data has a more complex data structure than the insurance claims data.

Download Full-text

Identifying Key Fraud Indicators in the Automobile Insurance Industry Using SQL Server Analysis Services

Studia Universitatis Babe-Bolyai Oeconomica ◽

10.2478/subboec-2019-0009 ◽

2019 ◽

Vol 64 (2) ◽

pp. 53-71

Author(s):

Botond Benedek ◽

Ede László

Keyword(s):

Neural Network ◽

Decision Tree ◽

Naive Bayes ◽

Insurance Industry ◽

Naïve Bayes ◽

Sql Server ◽

Categorical Variables ◽

Automobile Insurance ◽

Price Determination ◽

Mining Tool

Abstract Customer segmentation represents a true challenge in the automobile insurance industry, as datasets are large, multidimensional, unbalanced and it also requires a unique price determination based on the risk profile of the customer. Furthermore, the price determination of an insurance policy or the validity of the compensation claim, in most cases must be an instant decision. Therefore, the purpose of this research is to identify an easily usable data mining tool that is capable to identify key automobile insurance fraud indicators, facilitating the segmentation. In addition, the methods used by the tool, should be based primarily on numerical and categorical variables, as there is no well-functioning text mining tool for Central Eastern European languages. Hence, we decided on the SQL Server Analysis Services (SSAS) tool and to compare the performance of the decision tree, neural network and Naïve Bayes methods. The results suggest that decision tree and neural network are more suitable than Naïve Bayes, however the best conclusion can be drawn if we use the decision tree and neural network together.

Download Full-text

bCNN-Methylpred: Feature-Based Prediction of RNA Sequence Modification Using Branch Convolutional Neural Network

Genes ◽

10.3390/genes12081155 ◽

2021 ◽

Vol 12 (8) ◽

pp. 1155

Author(s):

Naeem Islam ◽

Jaebyung Park

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Domain Knowledge ◽

Feature Space ◽

Experimental Methods ◽

Machine Learning Techniques ◽

Rna Modification ◽

Biological Processes ◽

Rna Sequence ◽

Functional Mechanisms

RNA modification is vital to various cellular and biological processes. Among the existing RNA modifications, N6-methyladenosine (m6A) is considered the most important modification owing to its involvement in many biological processes. The prediction of m6A sites is crucial because it can provide a better understanding of their functional mechanisms. In this regard, although experimental methods are useful, they are time consuming. Previously, researchers have attempted to predict m6A sites using computational methods to overcome the limitations of experimental methods. Some of these approaches are based on classical machine-learning techniques that rely on handcrafted features and require domain knowledge, whereas other methods are based on deep learning. However, both methods lack robustness and yield low accuracy. Hence, we develop a branch-based convolutional neural network and a novel RNA sequence representation. The proposed network automatically extracts features from each branch of the designated inputs. Subsequently, these features are concatenated in the feature space to predict the m6A sites. Finally, we conduct experiments using four different species. The proposed approach outperforms existing state-of-the-art methods, achieving accuracies of 94.91%, 94.28%, 88.46%, and 94.8% for the H. sapiens, M. musculus, S. cerevisiae, and A. thaliana datasets, respectively.

Download Full-text

Assessing the clinical utility of genetic risk scores for targeted cancer screening

Journal of Translational Medicine ◽

10.1186/s12967-020-02699-w ◽

2021 ◽

Vol 19 (1) ◽

Author(s):

Carly A. Conran ◽

Zhuqing Shi ◽

William Kyle Resurreccion ◽

Rong Na ◽

Brian T. Helfand ◽

...

Keyword(s):

Colorectal Cancer ◽

Primary Care ◽

High Risk ◽

Risk Score ◽

Genetic Risk ◽

Clinical Utility ◽

Low Risk ◽

Risk Scores ◽

Average Risk ◽

Genetic Risk Scores

Abstract Background Genome-wide association studies have identified thousands of disease-associated single nucleotide polymorphisms (SNPs). A subset of these SNPs may be additively combined to generate genetic risk scores (GRSs) that confer risk for a specific disease. Although the clinical validity of GRSs to predict risk of specific diseases has been well established, there is still a great need to determine their clinical utility by applying GRSs in primary care for cancer risk assessment and targeted intervention. Methods This clinical study involved 281 primary care patients without a personal history of breast, prostate or colorectal cancer who were 40–70 years old. DNA was obtained from a pre-existing biobank at NorthShore University HealthSystem. GRSs for colorectal cancer and breast or prostate cancer were calculated and shared with participants through their primary care provider. Additional data was gathered using questionnaires as well as electronic medical record information. A t-test or Chi-square test was applied for comparison of demographic and key clinical variables among different groups. Results The median age of the 281 participants was 58 years and the majority were female (66.6%). One hundred one (36.9%) participants received 2 low risk scores, 99 (35.2%) received 1 low risk and 1 average risk score, 37 (13.2%) received 1 low risk and 1 high risk score, 23 (8.2%) received 2 average risk scores, 21 (7.5%) received 1 average risk and 1 high risk score, and no one received 2 high risk scores. Before receiving GRSs, younger patients and women reported significantly more worry about risk of developing cancer. After receiving GRSs, those who received at least one high GRS reported significantly more worry about developing cancer. There were no significant differences found between gender, age, or GRS with regards to participants’ reported optimism about their future health neither before nor after receiving GRS results. Conclusions Genetic risk scores that quantify an individual’s risk of developing breast, prostate and colorectal cancers as compared with a race-defined population average risk have potential clinical utility as a tool for risk stratification and to guide cancer screening in a primary care setting.

Download Full-text

An Evaluation of the New Japanese Bonus–Malus System with No-claim and Claimed Subclasses

Asia-Pacific Journal of Risk and Insurance ◽

10.1515/apjri-2019-0004 ◽

2020 ◽

Vol 0 (0) ◽

Author(s):

Mahito Okura ◽

Takuya Yoshizawa ◽

Motohiro Sakaki

Keyword(s):

Simulation Analysis ◽

Insurance Premium ◽

Automobile Insurance ◽

Insurance Claims ◽

Present Value ◽

Time Discount

AbstractThe purpose of this research is to evaluate the new Japanese Bonus–Malus System (BMS 2012) in automobile insurance, which is an unusual system wherein both no-claim and claimed subclasses exist. To evaluate BMS 2012, we conduct a simulation analysis and compare BMS 2012 with the former Japanese BMS (BMS 2009) in terms of the present value of the total insurance premium that is closely related to the frequency of insurance claims. Based on the comparison, our main conclusion is that BMS 2012 offers more effects to lower the frequency of insurance claims than BMS 2009 does when the policyholders’ classes in BMS are high classes that evaluate as safety drivers, time discount and/or renewal rates are relatively low, and the policyholders’ risk averseness is large.

Download Full-text