Index tracking optimization with cardinality constraint: a performance comparison of genetic algorithms and tabu search heuristics

García, Fernando; Guijarro, Francisco; Oliver, Javier

doi:10.1007/s00521-017-2882-2

Cited by 38 publications

(24 citation statements)

References 42 publications

(71 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tabu Search (TS) [11,12] is characterized by simulating the memory process of human beings and adopting Tabu technology [13,14], that is, the previous work is prohibited to avoid the local optimal situation in local neighborhood Search [15]. The idea of tabu search algorithm is to select the appropriate candidate set in the initial solution neighborhood with the given initial solution and neighborhood.…”

Section: Tabu Search Algorithmmentioning

confidence: 99%

Novel KNN Algorithms for Spherical Regions Based on Clustering and Region Division

Hwh¹,

Pxp

Jzj

2021

Preprint

View full text Add to dashboard Cite

The KNN classification algorithm is one of the most commonly used algorithm in the AI field. But classical KNN classification algorithm does not preprocess data before classification calculation, which results in a long time required for classification and a decrease in classification accuracy. To solve the above problems, this paper proposes two improved algorithms, namely KNNTS, and KNNTS-PK+. The two improved algorithms are based on KNNPK+ algorithm, which uses PK-Means + + algorithm to select the center of the spherical region, and sets the radius of the region to form a sphere to divide the data set in the space. The KNNPK+ algorithm improves the classification accuracy on the premise of stabilizing the classification efficiency of KNN classification algorithm. In order to improve the classification efficiency of KNN algorithm on the premise that the accuracy of KNN classification algorithm remains unchanged, KNNTS algorithm is proposed. It uses tabu search algorithm to select the radius of spherical region, and uses spherical region division method with equal radius to divide the data set in space. On the basis of the first two improved algorithms, KNNTS-PK+ algorithm combines them to divide the data sets in space. After preprocessing the data by two methods, experiments are carried out on the new data set and the classification results were obtained. Results revealed show that the two improved algorithms can effectively improve the classification accuracy and efficiency after the data samples are cut reasonably.

show abstract

Section: Tabu Search Algorithmmentioning

confidence: 99%

Novel KNN Algorithms for Spherical Regions Based on Clustering and Region Division

Hwh¹,

Pxp

Jzj

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…As mentioned earlier, stock selection and capital allocation are the two fundamental issues for partial (replication) index tracking (García, Guijarro, and Oliver 2017). The former concerns determining which stocks should be included in the portfolio while the latter aims to optimally allocate capital among the chosen stocks to minimise the tracking error.…”

Section: Related Workmentioning

confidence: 99%

“…The 0 norm has been widely used as the sparsity constraint to construct a sparse tracking portfolio (Benidis, Feng, and Palomar 2018). However, imposing the 0 constraint makes the regularised regression problem NP-hard and requires search heuristics, such as genetic algorithms (Ni and Wang 2013;Li, Sun, and Bao 2011;García, Guijarro, and Oliver 2017), Tabu search (García, Guijarro, and Oliver 2017), simulated annealing (Chang et al 2000;Woodside-Oriakhi, Lucas, and Beasley 2011) and transformation (Coleman, Li, and Henniger 2006;Wang et al 2012). These algorithms are not guaranteed to find the optimal solution, and in many situations the search space grows super-linearly.…”

Section: Related Workmentioning

confidence: 99%

Index Tracking with Cardinality Constraints: A Stochastic Neural Networks Approach

Zheng

Chen

Hospedales

et al. 2020

AAAI

View full text Add to dashboard Cite

Partial (replication) index tracking is a popular passive investment strategy. It aims to replicate the performance of a given index by constructing a tracking portfolio which contains some constituents of the index. The tracking error optimisation is quadratic and NP-hard when taking the ℓ0 constraint into account so it is usually solved by heuristic methods such as evolutionary algorithms. This paper introduces a simple, efficient and scalable connectionist model as an alternative. We propose a novel reparametrisation method and then solve the optimisation problem with stochastic neural networks. The proposed approach is examined with S&P 500 index data for more than 10 years and compared with widely used index tracking approaches such as forward and backward selection and the largest market capitalisation methods. The empirical results show our model achieves excellent performance. Compared with the benchmarked models, our model has the lowest tracking error, across a range of portfolio sizes. Meanwhile it offers comparable performance to the others on secondary criteria such as volatility, Sharpe ratio and maximum drawdown.

show abstract

“…In this case, the selection of the companies to be included in the portfolio is done simultaneously. When investors opt for a passive portfolio management, passive investment strategies are implemented (García et al, 2018a;Moeini, 2019). Investors preferring to adopt an active role and expecting to beat the market use other portfolio selection strategies (García et al, 2013(García et al, , 2020(García et al, , 2019aGoel et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

Multiobjective Approach to Portfolio Optimization in the Light of the Credibility Theory

García

González-Bueno

Guijarro

et al. 2020

Technological and Economic Development of Economy

Self Cite

View full text Add to dashboard Cite

The present research proposes a novel methodology to solve the problems faced by investors who take into consideration different investment criteria in a fuzzy context. The approach extends the stochastic mean-variance model to a fuzzy multiobjective model where liquidity is considered to quantify portfolio’s performance, apart from the usual metrics like return and risk. The uncertainty of the future returns and the future liquidity of the potential assets are modelled employing trapezoidal fuzzy numbers. The decision process of the proposed approach considers that portfolio selection is a multidimensional issue and also some realistic constraints applied by investors. Particularly, this approach optimizes the expected return, the risk and the expected liquidity of the portfolio, considering bound constraints and cardinality restrictions. As a result, an optimization problem for the constraint portfolio appears, which is solved by means of the NSGA-II algorithm. This study defines the credibilistic Sortino ratio and the credibilistic STARR ratio for selecting the optimal portfolio. An empirical study on the S&P100 index is included to show the performance of the model in practical applications. The results obtained demonstrate that the novel approach can beat the index in terms of return and risk in the analyzed period, from 2008 until 2018.

show abstract

Index tracking optimization with cardinality constraint: a performance comparison of genetic algorithms and tabu search heuristics

Cited by 38 publications

References 42 publications

Novel KNN Algorithms for Spherical Regions Based on Clustering and Region Division

Novel KNN Algorithms for Spherical Regions Based on Clustering and Region Division

Index Tracking with Cardinality Constraints: A Stochastic Neural Networks Approach

Multiobjective Approach to Portfolio Optimization in the Light of the Credibility Theory

Contact Info

Product

Resources

About