Monte Carlo scalable algorithms for Computational Finance

Alexandrov, Vassil; González-Martel, Christian; Straßburg, Janko

doi:10.1016/j.procs.2011.04.185

Cited by 6 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…c) Optimal strategy in presence of traffic: to identify the optimal strategy in presence of traffic, we propose an evaluation metrics based on Stochastic Dynamic Programming (SDP) [12], [13]. The dataset used by SDP is generated through the Monte Carlo (MC) [14] simulations, relying on a multi-agent influence/reaction model and on the previously computed statistics of the competitors.…”

Section: Statement Of Contributionsmentioning

confidence: 99%

Competitors-Aware Stochastic Lap Strategy Optimisation for Race Hybrid Vehicles

Braghin¹,

Paparusso²,

Riani³

et al. 2022

Preprint

View full text Add to dashboard Cite

World Endurance Championship (WEC) racing events are characterised by a relevant performance gap among competitors. The fastest vehicles category, consisting in hybrid vehicles, has to respect energy usage constraints set by the technical regulation. Considering absence of competitors, i.e. traffic conditions, the optimal energy usage strategy for lap time minimisation is typically computed through a constrained optimisation problem. To the best of our knowledge, the majority of state-of-the-art works neglects competitors. This leads to a mismatch with the real world, where traffic generates considerable time losses. To bridge this gap, we propose a new framework to offline compute optimal strategies for the powertrain energy management considering competitors. Through analysis of the available data from previous events, statistics on the sector times and overtaking probabilities are extracted to encode the competitors' behaviour. Adopting a multi-agent model, the statistics are then used to generate realistic Monte Carlo (MC) simulation of their position along the track. The simulator is then adopted to identify the optimal strategy as follows. We develop a longitudinal vehicle model for the ego-vehicle and implement an optimisation problem for lap time minimisation in absence of traffic, based on Genetic Algorithms. Solving the optimisation problem for a variety of constraints generates a set of candidate optimal strategies. Stochastic Dynamic Programming is finally implemented to choose the best strategy considering competitors, whose motion is generated by the MC simulator. Our approach, validated on data from a real stint of race, allows to significantly reduce the lap time.

show abstract

Section: Statement Of Contributionsmentioning

confidence: 99%

Competitors-Aware Stochastic Lap Strategy Optimisation for Race Hybrid Vehicles

Braghin¹,

Paparusso²,

Riani³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The Monte Carlo method was suggested for the enhancement of screening capabilities in engineering fields (Rosenbloom, 1996;Wey, 2008). This statistical method also has been applied in various areas such as engineering (e.g., Dimov and Georgieva, 2010), medicine (e.g., Oakley et al, 2010), and the finance and banking sectors (e.g., Alexandrov et al, 2011). Furthermore, a researcher (Rosenbloom, 1996) has argued that integration of Monte Carlo analysis in the AHP is able to increase the overall decision-making capability.…”

Section: Monte Carlo Analysismentioning

confidence: 99%

Use of an Analytic Network Process and Monte Carlo Analysis in New Product Formula Selection Decisions

Wudhikarn

Chakpitak²,

Neubert³

2015

Asia Pac. J. Oper. Res.

View full text Add to dashboard Cite

One crucial matter in routine life is decision-making. Although decision-making in everyday life appears to be easily dealt with by one-on-one comparisons, the same is not true with decision-making in business. In business management decisions, problems are more complicated than those in individual life because most business situations fall into the category of multi-criteria decision-making (MCDM) problems. Therefore, appropriate multi-criteria decision methods should be carefully selected to solve these problems. This study uses the analytic network process (ANP), one of the widely available multi-criteria decision methods. However, this popular method generally ignores the uncertainty inherent in the input data. Therefore, this paper proposes an improved process that considers uncertainty by using Monte Carlo analysis with input values then applied to the ANP procedures. This proposed method is implemented by a real business that produces roof tiles; the primary goal of the study is to select among newly developed roof formulas by considering the uncertainty and interrelation among decision criteria and elements as well as alternatives. The outcomes of study accurately rank the new product formulas. Furthermore, the results of improved method differ the rankings produced by the original ANP. The observed dissimilarities mainly result from uncertainty consideration discussed in this study. be independent from other elements, but, in fact, most real-life problems involve interaction as well as dependency among elements (Saaty, 2001). Thus, an improved method, the analytic network process (ANP), was developed to overcome this problem. The ANP is extended to consider both dependency and feedback. For these reasons, the ANP was later consolidated with several quality methods to produce an improved and more comprehensive decision-making method (Kahraman et al., 2006). However, ANP approximates the prioritization of the competing candidates. Eigenvalues from ANP are calculated from interrelations among input data computations and are normally applied as a basis of prioritization; however, they still lack inclusion of the uncertainty and probability information and lead to inappropriate decision-making (Wey, 2008;Hsu and Pan, 2009).Normally, there is available research that considers the uncertainty in single input data such as the calculation of cost or quality; nevertheless, there has been little attention focused on the uncertainty between cost and quality coordination in MCDM problems. Moreover, most of ANP studies largely ignored the uncertainty (Huang and Tzeng, 2007). Generally, MCDM anticipates the costs, opportunity, benefits, resource consumption, material supplies and other factors, but the exact values of these various attributes are difficult to estimate. Thus, decision-makers may be operating with incomplete knowledge as to the complete data values. Consequently, uncertainty must be included in the data. Some researchers have proposed using the integrated MCDM with an uncertainty module. Lee and Kim (200...

show abstract

“…The result of Monte-Carlo simulation can be efficient and correct due to the advancement of technology and efficient algorithm (Chen & Hong, 2007). Regarding the research on improving and implementation of computational power on computational finance is conducted by Alexandrov et al (2011), in which Alexandrov et al (2011) implementing the parallel Monte-Carlo algorithms and its potential based on the scalability, speed and fault-tolerance perspectives in computational finance. In order to implement the Monte-Carlo simulation, the following steps is given as follows: (1) design or choose stochastic process for the risk factor, (2) generate random variables to represent risk factor at the determined horizon, (3) calculate the values of the portfolios based on the determined horizon and finally, (5) calculate the result based on the specified iterations on the simulations.…”

Section: Introductionmentioning

confidence: 99%

Exchange Rate Forecasting and Value-at-Risk Estimation on Indonesian Currency Using Copula Method

Sirait¹,

Simatupang²

2019

Proceedings of the 3rd International Conference on Accounting, Management and Economics 2018 (ICAME 2018)

View full text Add to dashboard Cite

This study aims to determine the future value and the value-at-risk estimation of four selected currencies, namely United States Dollar (USD), Australian Dollar (AUD), European Union Euro (EUR) and Japanese Yen (JPY) against Indonesian Rupiah (IDR). The Monte-Carlo simulation is implemented to estimate the future value of each currency relationship and integrating it with the concept from the copula method; the risk value estimation is conducted using Value-at-Risk (VaR), and the VaR estimation is within the range of 90%, 95% and 99% confidence interval. The copula method we use in this study is Clayton copula because it has the highest log-likelihood value compared to Frank and Gumbel copula; with an addition, each currency uses their regressive model to see if the selected exchange rates have the characteristic of a seasonal or non-seasonal pattern. The result we obtain in this study are JPY/IDR, and EUR/IDR relationships have the highest simulated loss and estimated risk values in each confidence interval.

show abstract

Monte Carlo scalable algorithms for Computational Finance

Cited by 6 publications

References 12 publications

Competitors-Aware Stochastic Lap Strategy Optimisation for Race Hybrid Vehicles

Competitors-Aware Stochastic Lap Strategy Optimisation for Race Hybrid Vehicles

Use of an Analytic Network Process and Monte Carlo Analysis in New Product Formula Selection Decisions

Exchange Rate Forecasting and Value-at-Risk Estimation on Indonesian Currency Using Copula Method

Contact Info

Product

Resources

About