Dynamic Bayesian Networks Application for Evaluating the Investment Projects Effectiveness

Lytvynenko, Volodymyr; Naumov, Oleksandr; Voronenko, Mariia; Krejčí, Jan; Наумова, Лариса Миколаївна; Nikytenko, Dmytro; Савіна, Наталія

doi:10.1007/978-3-030-54215-3_20

Cited by 4 publications

(4 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Definition 2.2. [14] According to the CPT, the value of the discrete r.v.s X (called 'prospect' in [14]) is given by…”

Section: Prospect Theorymentioning

confidence: 99%

“…and w − (.) are weighing functions for the domains of gains and losses defined from [11] or [14], respectively. Also, we need w + (.)…”

Section: Prospect Theorymentioning

confidence: 99%

“…A few years later, the anticipated utility theory was established by (Quiggin,1982) [20], Yaari,1984 [25], and (Segal,1984) [22]. Moreover, non-expected utility theories such as prospect theory are observed by (Kahneman and Tversky, 1979)and developed later by (Kahneman and Tversky, 1992) [14], (Perelec, 1998) [19]. In addition, Trversky (1979,1992) [13], [17] gave us brief guidance on how to choose an appropriate reference point.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Probability Function among Investors using Prospect Theory

Almualim,

Shafqat

2024

Preprint

View full text Add to dashboard Cite

In this study, we test an investor's market behavior using probability functions. Furthermore, by establishing a consistent mean-variance model based on compound independent axioms with a unique certainty equivalency C = u −1 (E(u(X)], we present an alternate strategy to solve cooperative investment in a dynamic manner for mean-variance utility function. As a result, an explicit formula based on the exponential utility function over the normal distribution is established to approximate the certainty equivalent for each investor corresponding to the mean-variance utility function. Furthermore, we dene how alternative decision-making theories, like prospect theory, can be applied to solve cooperative investment schemes by taking investors' preferences into account as a function of choice, and we make the assumption that weight does not always have to coincide with probability. Therefore, Prospect Theory (PT) argues that decision weights have a tendency to underweight moderate and high probabilities and overweight small ones. Furthermore, the Prospect Theory Approach can be used to make investors' perceptions of risk consistent with logical decision-making through the use of suitable modeling. Additionally, a numerical experiment using S&P100 data is displayed.

show abstract

“…Definition 2.2. [14] According to the CPT, the value of the discrete r.v.s X (called 'prospect' in [14]) is given by…”

Section: Prospect Theorymentioning

confidence: 99%

“…and w − (.) are weighing functions for the domains of gains and losses defined from [11] or [14], respectively. Also, we need w + (.)…”

Section: Prospect Theorymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Probability Function among Investors using Prospect Theory

Almualim,

Shafqat

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Static BN have found their application in medicine [9], genetics [20], and epidemiology [16]. The scope of dynamic BN application is also very wide [8,15,17,24]. Bayesian approach works even with incomplete and inaccurate input data, with noise and missing values.…”

Section: Related Workmentioning

confidence: 99%

An Expert System Prototype for the Early Diagnosis of Pneumonia

Voronenko

Kovalchuk

Lytvynenko

et al. 2021

Lecture Notes in Computational Intelligence and Decision Making

Self Cite

View full text Add to dashboard Cite

In this paper, an expert system model prototype based on Bayesian networks is proposed, which makes it possible to provide assistance to a doctor in the early diagnosis of a disease such as "pneumonia". We designed a static Bayesian network with five key variables to obtain the probabilistic inference of the resulting node that determines the presence or absence of disease in a patient. We consulted with medical experts when selecting and quantifying input and output variables. When constructing a Bayesian model and conducting scenario analysis for a better prognosis of the diagnosis, we consulted with the attending physicians.

show abstract