journal article
LitStream Collection
Home
Castellani, Gilberto; Fiore, Ugo; Marino, Zelda; Passalacqua, Luca; Perla, Francesca; Scognamiglio, Salvatore; Zanetti, Paolo
2021 Applied Stochastic Models in Business and Industry
doi: 10.1002/asmb.2607
The insurance regulatory regime introduced in the European Union by the “Solvency II” Directive 2009/138, that has become applicable on 1 January 2016, is aimed to safeguard policyholders and beneficiaries by requiring insurance undertakings to hold own funds able to cover losses, in excess to the expected ones, at the 99.5% confidence level, over a 1‐year period. In order to assess risks and evaluate the regulatory Solvency Capital Requirement, undertakings should compute the probability distribution of the Net Asset Value over a 1‐year period, with a financially inspired market consistent approach. In life insurance, given the peculiarities of the contracts, the valuation of the Net Asset Value distribution requires a nested Monte Carlo simulation, which is extremely time‐consuming. Machine learning techniques are considered a promising candidate to reduce the computational burden of nested simulations. This work investigates the potential of well‐established methods, such as deep learning networks and support vector regressors, when applied to the valuation of the Solvency Capital Requirement of participating life insurance policies, by empirically assessing their effectiveness and by comparing their efficiency and accuracy, also w.r.t. the “traditional” least squares Monte Carlo technique. The work aims also to contribute to the global process of renewal of the European insurance industry, where Solvency II has made the board of directors fully responsible of the choice of evaluation techniques and algorithmic processes, under the periodic monitoring of national supervisory authorities.
Frigau, Luca; Contu, Giulia; Mola, Francesco; Conversano, Claudio
2021 Applied Stochastic Models in Business and Industry
doi: 10.1002/asmb.2618
Semisupervised clustering extends standard clustering methods to the semisupervised setting, in some cases considering situations when clusters are associated with a given outcome variable that acts as a “noisy surrogate,” that is a good proxy of the unknown clustering structure. In this article, a novel approach to semisupervised clustering associated with an outcome variable named network‐based semisupervised clustering (NeSSC) is introduced. It combines an initialization, a training and an agglomeration phase. In the initialization and training a matrix of pairwise affinity of the instances is estimated by a classifier. In the agglomeration phase the matrix of pairwise affinity is transformed into a complex network, in which a community detection algorithm searches the underlying community structure. Thus, a partition of the instances into clusters highly homogeneous in terms of the outcome is obtained. We consider a particular specification of NeSSC that uses classification or regression trees as classifiers and the Louvain, Label propagation and Walktrap as possible community detection algorithm. NeSSC's stopping criterion and the choice of the optimal partition of the original data are also discussed. Several applications on both real and simulated data are presented to demonstrate the effectiveness of the proposed semisupervised clustering method and the benefits it provides in terms of improved interpretability of results with respect to three alternative semisupervised clustering methods.
Ilter, Damla; Deniz, Eylem; Kocadagli, Ozan
2021 Applied Stochastic Models in Business and Industry
doi: 10.1002/asmb.2614
The credit scoring is a statistical analysis performed by financial institutions to represent the creditworthiness of an individual or small and medium‐sized enterprise. A credit score is a numerical quantity that can be qualified by a rating label showing the potential risk. In order to determine which customers are likely to bring in the most revenue at the exact interest rate and credit limits, the lenders take into accounts these credit scores. In this context, the robust statistical models are inevitable to reduce the number of wrong decisions in the credit evaluation process. Although the machine learning approaches provide superior performance to conventional statistical methods, they are mostly criticized due to the selection of model structure, model complexity, tuning parameters, time consumption in the high‐dimensional and excessive nonlinear cases. For this reason, this study introduces an efficient model estimation and feature selection procedure for artificial neural network (ANN) classifiers in the context of credit scoring. Essentially, this procedure hybridizes training of ANNs with a novel feature selection approach based on genetic algorithms and information complexity criterion. In the application, the proposed procedure was performed on a couple of benchmark credit scoring datasets. According to analysis results, the proposed approach not only estimates robust models from ANNs in terms of model complexity, feature selection, and time consumption, but also outperforms the traditional training procedure for the classification accuracies, false positive, and false negative errors overtraining and test datasets.
Pandolfo, Giuseppe; Iorio, Carmela; Staiano, Michele; Aria, Massimo; Siciliano, Roberta
2021 Applied Stochastic Models in Business and Industry
doi: 10.1002/asmb.2616
Even if large historical dataset could be available for monitoring key quality features of a process via multivariate control charts, previous knowledge may not be enough to reliably identify or adopt a unique model for all the variables. When no specific parametric model turns out to be appropriate, some alternative solutions should be adopted and exploiting non‐parametric methods to build a control chart appears a reasonable choice. Among the possible non‐parametric statistical techniques, data depth functions are gaining a growing interest in multivariate quality control. Within the literature, several notions of depth are effective for this purpose, even in the case of deviation from the normality assumption. However, the use of the Lp depth for constructing non‐parametric multivariate control charts has been surprisingly neglected so far. Hence, the goal of this work is to investigate the behavior the Lp depth in the statistical process control and to compare its performances to those of the Mahalanobis depth, which is often adopted to build depth‐based control charts.
Wang, Feifei; Yang, Yang; Tso, Geoffrey K. F.; Li, Yang
2021 Applied Stochastic Models in Business and Industry
doi: 10.1002/asmb.2575
Crowdfunding has emerged as a major way to raise financial supports through collaborative contributions of the general public. In recent studies, promotional activities are found to be highly influential to the final outcome of crowdfunding projects. In order to conduct effective and efficient promotional campaigns, it is essential to contiguously monitor their progress status and investigate the determinants to their success during the whole fundraising process. It can help project starters and fundraisers to make decisions on whether and how to adjust the promotional campaigns to make them more useful. To this end, we propose a prediction framework for social influence, an evaluation for success of social promotions, and utilize knowledge gained from both crowdfunding websites and social networks to facilitate the promotional activities. Under two influence definitions based on reshare count and followers count, we find that knowledge gained from aggregate data rather than incremental data is better indicators of the social influence growth. We also discover that some features, including “value of pledged funds” and “number of total promoters,” are of great importance to social influence within the fundraising durations. All these findings could help project starters and fundraisers to make decisions on devising effective social promotions.
Su, Xiaonan; Wang, Xinzhi; Yang, Yang
2021 Applied Stochastic Models in Business and Industry
doi: 10.1002/asmb.2561
Consider a risk model in which X1,…, Xn are n potential losses from different risky assets at the terminal time, and θ1,…,θn are n discount factors over the period. In this paper, we establish some asymptotic formulas for the value at risk and conditional tail expectation of the total discounted loss Sn=∑i=1nθiXi of an investment portfolio. We also demonstrate our obtained results through Monte Carlo simulations with asymptotics.
Ding, Weiyong; Wang, Chuchu; Zhang, Yiying
2021 Applied Stochastic Models in Business and Industry
doi: 10.1002/asmb.2562
The generalized aggregation ∑i=1nWiϕ(Xi,ai) arises in many research fields including applied probability, actuarial science, and reliability theory, where ϕ is a bivariate kernel function and a is a parameter vector. One of its remarkable features is that both X and W are dependent in many practical situations. Therefore, studying the stochastic properties of generalized aggregations under various dependence structures is an interesting and meaningful problem. In this paper, by using left tail weakly stochastic arrangement increasing, right tail weakly stochastic arrangement increasing, and comonotonicity to characterize the dependent structures among X or W, we establish the increasing convex ordering and the expectation ordering of generalized aggregations to investigate the effects of the arrangement and heterogeneity among ai's. Numerical examples and three practical applications are presented to illustrate our results as well.
Arriaza, Antonio; Sordo, Miguel A.
2021 Applied Stochastic Models in Business and Industry
doi: 10.1002/asmb.2565
The preservation of stochastic orders by distortion functions has become a topic of increasing interest in the reliability analysis of coherent systems. The reason of this interest is that the reliability function of a coherent system with identically distributed components can be represented as a distortion function of the common reliability function of the components. In this framework, we study the preservation of the excess wealth order, the total time on test transform order, the decreasing mean residual live order, and the quantile mean inactivity time order by distortion functions. The results are applied to study the preservation of these stochastic orders under the formation of coherent systems with exchangeable components.
Showing 1 to 10 of 14 Articles