Lukasz Delong

Prof. Lukasz Delong


Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 March 2007 in Mathematical Methods of Operations Research
Verified
Journal Article
Closed access
PDF file
LDLukasz Delong
Lukasz Delong
RGRussell Gerrard
Russell Gerrard

20 January 2015 in ASTIN Bulletin
Verified
Journal Article
Closed access
PDF file
An ChenAn Chen
An Chen
LDLukasz Delong
Lukasz Delong
We study an asset allocation problem for a defined-contribution (DC) pension scheme in its accumulation phase. We assume that the amount contributed to the pension fund by a pension plan member is coupled with the salary income which fluctuates randomly over time and contains both a hedgeable and non-hedgeable risk component. We consider an economy in which macroeconomic risks are existent. We assume that the economy can be in one ofIstates (regimes) and switches randomly between those states. The state of the economy affects the dynamics of the tradeable risky asset and the contribution process (the salary income of a pension plan member). To model the switching behavior of the economy we use a counting process with stochastic intensities. We find the investment strategy which maximizes the expected exponential utility of the discounted excess wealth over a target payment, e.g. a target lifetime annuity.

24 April 2023 in ASTIN Bulletin
Verified
Journal Article
Open access
PDF file
LDLukasz Delong
Lukasz Delong
AKAnna Kozak
Anna Kozak
We focus on modelling categorical features and improving predictive power of neural networks with mixed categorical and numerical features in supervised learning tasks. The goal of this paper is to challenge the current dominant approach in actuarial data science with a new architecture of a neural network and a new training algorithm. The key proposal is to use a joint embedding for all categorical features, instead of separate entity embeddings, to determine the numerical representation of the categorical features which is fed, together with all other numerical features, into hidden layers of a neural network with a target response. In addition, we postulate that we should initialize the numerical representation of the categorical features and other parameters of the hidden layers of the neural network with parameters trained with (denoising) autoencoders in unsupervised learning tasks, instead of using random initialization of parameters. Since autoencoders for categorical data play an important role in this research, they are investigated in more depth in the paper. We illustrate our ideas with experiments on a real data set with claim numbers, and we demonstrate that we can achieve a higher predictive power of the network.

1 January 2019 in ASTIN Bulletin
Verified
Journal Article
Closed access
PDF file
LDLukasz Delong
Lukasz Delong
Jan DhaeneJan Dhaene
Jan Dhaene
Karim BarigouKarim Barigou
Karim Barigou
Delong et al. (2018) presented a theory of fair (market-consistent and actuarial) valuation of insurance liability cash-flow streams in continuous time. In this paper, we investigate in detail two practical applications of our theory of fair valuation. In the first example, we consider the fair valuation of a terminal benefit which is contingent on correlated tradeable and non-tradeable financial risks. In the second example, we consider a portfolio of unit-linked contracts contingent on a non-tradeable insurance and a tradeable financial risk. We derive partial differential equations (PDEs) which characterize the continuous-time fair valuation operators in these two examples and we find explicit solutions to these PDEs. The fair values of the liabilities are decomposed into the best estimate of the liability and a risk margin. The arbitrage-free representations of the fair values of the liabilities are derived and the dynamic hedging strategies associated with the continuous-time fair valuation operators are also established. Detailed interpretations of the results, which should be useful both for researchers and practitioners, are provided.

13 February 2021 in European Actuarial Journal
Verified
Journal Article
Open access
PDF file
LDLukasz Delong
Lukasz Delong
MLMathias Lindholm
Mathias Lindholm
MWMario Wüthrich
Mario Wüthrich
The most commonly used regression model in general insurance pricing is the compound Poisson model with gamma claim sizes. There are two different parametrizations for this model: the Poisson-gamma parametrization and Tweedie’s compound Poisson parametrization. Insurance industry typically prefers the Poisson-gamma parametrization. We review both parametrizations, provide new results that help to lower computational costs for Tweedie’s compound Poisson parameter estimation within generalized linear models, and we provide evidence supporting the industry preference for the Poisson-gamma parametrization.

1 April 2022 in Journal of Computational and Applied Mathematics
Verified
Journal Article
Closed access
Karim BarigouKarim Barigou
Karim Barigou
LDLukasz Delong
Lukasz Delong