Alma Braimllari

Insurance is essential for financial risk protection, but claim management is complex and requires accurate classification and forecasting strategies. This study aimed to empirically evaluate the performance of classification algorithms, including Logistic Regression, Decision Tree, Random Forest, XGBoost, K-Nearest Neighbors, Support Vector Machine, and Naïve Bayes to predict high insurance claims. The research analyses the variables of claims, vehicles, and insured parties that influence the classification of high-cost claims. This investigation utilizes a dataset comprising 802 observations of bodily injury claims from the motor liability portfolio of a private insurance company in Albania, covering the period from 2018 to 2024. In order to evaluate and compare the performance of the models, we employed evaluation criteria, including classification accuracy (CA), area under the curve (AUC), confusion matrix, and error rates. We found that Random Forest performs better, achieving the highest classification accuracy (CA = 0.8867, AUC = 0.9437) with the lowest error rates, followed by the XGBoost model. At the same time, logistic regression demonstrated the weakest performance. Key predictive factors in high claim classification include claim type, deferred period, vehicle brand and age of driver. These findings highlight the potential of machine learning models in improving claim classification and risk assessment and refine underwriting policy.

To guarantee the fulfillment of all claims, an insurance company must allocate enough funds to cover both current and future claims for active policies. The application of stochastic models has found extensive use in various domains of insurance and finance. However, their application in the context of private health insurance has been somewhat limited. To address this gap in existing knowledge, this paper aims to explore the application of stochastic methods to disease portfolios. The study involves dividing the developmental periods into semi-annual intervals and determining the most appropriate model for forecasting claim reserves. The research objectives include evaluating the effectiveness of the Mack, Clark LDF, and Clark Cape Cod methods in predicting claim reserves within a disease portfolio. Moreover, the study intends to compare these models to identify the most appropriate method for claim reserve calculations. The data source employed for this study comprises private health insurance claims data covering the period from 2018 to 2022. When compared to alternative methods, The Clark LDF method with Weibull distribution is far more accurate in calculating the reserve of claims compared with other similar methods. From the pool of models analyzed, the Mack model and Clark LDF model with Weibull distribution show the lowest reserve claims and standard errors. Based on these result analyses, the insurance company is recommended to explore other strategies for its fund distribution as opposed to maintaining only one substantial claim reserve.

This study has taken into consideration the most important factors that influence consumers’ choice of clothing by analyzing some of the most popular brands in the market. The study was completed in two countries making a comparison between the preferences of consumers in a developed and developing country. The method used is the Analytic Hierarchy Process (AHP), which, by structuring the problem, makes it easier to classify the criteria that influence consumers’ evaluation of clothing brands. Six main criteria, sixteen sub-criteria, and different fast fashion brands were considered. The results of this method revealed different priorities regarding the criteria between the two regions even though the most preferred brand was the same. These results help the companies included in the study to not only improve their products, but to have a better approach to the customer, and strengthen their competitiveness.

Private health insurance plays a crucial role in the financing of healthcare in numerous states. Health insurance providers offer a diverse range of coverage options to ensure financial protection against unexpected losses caused by accidents or diseases. An event that prompts the insured to file a claim is known as a claim event. An insurance firm must set aside enough money to pay current and future claims for active policies to guarantee that all claims are fulfilled. The aim of this paper is to investigate whether deterministic methods and the bootstrap method can be used effectively to forecast claim reserves for a health insurance portfolio. The study is divided into two parts, each with its own specific objective. The first part presents and analyzes two different techniques utilized in estimating loss reserves: the chain ladder method and the Bornhuetter-Ferguson method. The second part focuses on employing the bootstrap method to generate an approximate predictive distribution for future random losses. The data utilized in this research paper comprises secondary data acquired from the personal sickness portfolio of an Albanian insurance company for the period spanning from 2018 to 2022. The reserves calculated using the Bootstrap method is lower than those computed using CL and BF methods. This conclusion suggests that the insurance company can consider alternative ways to allocate its funds instead of maintaining a large claim reserve. The prediction of reserves for all events up to the next 4 periods is accomplished through the use of CL and bootstrap methods.

Exports of goods and services represent one of the most important sources of foreign exchange income that alleviate the pressure on the balance payment and create employment opportunities. Exports’ opportunities in Albania for food products have been increasing significantly, but still they are far from their real capacity. This study is an attempt to model and forecast the monthly export of food, beverages and tobacco products of Albania, using the seasonal autoregressive integrated moving average (SARIMA) methodology. The data used are covering the period 2005:M1-2015:M12, and are taken from the database of National Institute of Statistics of Albania. Unit root tests are used to test the stationarity of the series. Autocorrelation and partial autocorrelation functions are used to identify the most suitable SARIMA model, in explaining the time series and forecasting the future monthly food exports. The residuals of the best fitted model are used for the diagnostic checking. The results indicate that the best fitted model is SARIMA (3,1,1)x(1,1,0)12. The best identified model for the data in the study is used to forecast monthly food exports up to the year 2017. These findings are useful for customers, producers and policymakers.

Factors Influencing the Usage of Online Shopping in Albania. Diamond Scientific Publishing is an international online publishing house.