A computing platform for pairs-trading online implementation via a blended Kalman-HMM filtering approach

Abstract

IntroductionPairs trading is an investment strategy used to exploit financial markets that are out of equilibrium. It consists of a long position in one security and a short position in another security at a predetermined ratio; see Elliott et al. [1]. Traders bet on the direction of the stocks relative to each other. Such a trading strategy is typically employed by hedge fund companies. Deviations in prices are monitored closely and used as basis for changing positions, taking advantage of market inefficiencies to obtain some profits. Hence, financial computing technologies with algorithmic trading capability, such as the one Abstract This paper addresses the problem of designing an efficient platform for pairs-trading implementation in real time. Capturing the stylised features of a spread process, i.e., the evolution of the differential between the returns from a pair of stocks, exhibiting a heavy-tailed mean-reverting process is also dealt with. Likewise, the optimal recovery of time-varying parameters in a return-spread model is tackled. It is important to solve such issues in an integrated manner to carry out the execution of trading strategies in a dynamic market environment. The Kalman and hidden Markov model (HMM) multiregime dynamic filtering approaches are fused together to provide a powerful method for pairs-trading actualisation. Practitioners' considerations are taken into account in the way the new filtering method is automated. The synthesis of the HMM's expectationmaximisation algorithm and Kalman filtering procedure gives rise to a set of self-updating optimal parameter estimates. The method put forward in this paper is a hybridisation of signal-processing algorithms. It highlights the critical role and beneficial utility of data fusion methods. Its appropriateness and novelty support the advancements of accurate predictive analytics involving big financial data sets. The algorithm's performance is tested on historical return spread between Coca-Cola and Pepsi Inc. 's equities. Through a back-testing trade, a hypothetical trader might earn a non-zero profit under the assumption of no transaction costs and bid-ask spreads. The method's success is illustrated by a trading simulation. The findings from this work show that there is high potential to gain when the transaction fees are low, and an investor is able to benefit from the proposed interplay of the two filtering methods. Tenyakov and Mamon J Big Data (2017) Data (2017) 4:46 put forward in this paper, are necessary for the efficient and successful implementation of a pairs trade. RESEARCHWhen the relative performance of the short position is better than that of the long position, this strategy is going to be profitable regardless of stock market regimes. So, a speculator who pairs a long position in a retail stock with a short position in a rival stock or an index ETF could end up with a profit. Pairs trading could be viewed alternatively as a mechanism to hedge both sector and market risks. When there is a financial crisis, two stoc...

H3O-LGBM: hybrid Harris hawk optimization based light gradient boosting machine model for real-time trading

“…The tenfold cross-validation methods are employed for picking testing and training datasets. Table 2 represents an analysis of correlation coefficients for four types of datasets with different methods such as Kalman and hidden Markov model (HMM) filtering method (Tenyakov and Mamon 2017 ), two robust long short-term memory (TRLSTM) (Fister et al 2021 ), long short–term memory(LSTM) recurrent neural networks (RNN) (Shen et al 2021 ), variational mode decomposition (VMD)-iterated cumulative sums of squares (ICSS)-bidirectional gated recurrent unit (BiGRU) (VMD-ICSS-BiGRU) (Li et al 2021 ), and Deep reinforcement learning (DRL) technique (Taghian et al 2022 ). From this table, the proposed method has high correlation coefficients compared with other methods.…”

“…The precious metal price forecast and stock market datasets are considered input datasets. Table 3 denotes the analysis of relative absolute error for four datasets with various methods like RNN-LSTM (Shen et al 2021 ), DRL (Taghian et al 2022 ), TRLSTM (Fister et al 2021 ), Kalman-HMM (Tenyakov and Mamon 2017 ), VMD-ICSS-BiGRU (Li et al 2021 ), and proposed. Among all those methods, the proposed method has a very low relative absolute error value and which shows the good performance of the proposed method.…”

“…The analysis of root means square error (RMSE) for different methods such as RNN-LSTM (Shen et al 2021 ), DRL (Taghian et al 2022 ), TRLSTM (Fister et al 2021 ), Kalman-HMM (Tenyakov and Mamon 2017 ), VMD-ICSS-BiGRU [12], and proposed Hybrid HHO-EFDM optimized LightGBM model are established in Table 4 . The proposed method has a very low RMSE value related to other methods.…”

“…Finally, the experimentation was carried out to determine the lower bound as well as the competitive ratio. Tenyakov et al ( 2017 ) presented the Kalman and hidden Markov model (HMM) filtering method to implement the pairs trading in real-time. The Kalman and the HMM design methods were blended together for providing a powerful approach to the actualization of pairs-trading.…”

Semantic Matching Efficiency of Supply and Demand Text on Cross‐Border E‐Commerce Online Technology Trading Platforms

“…Li et al proposed the TextCNN model in a paper published in 2019 and applied CNN to the field of natural language processing for text classification tasks [5]. Tenyakov and Mamon save more information in the form of vectors and at the same time train the capsule network with a dynamic routing mechanism [6], which reduces the parameters of the network and has a good effect on the handwritten digit recognition dataset [7]. Sun et al introduce the capsule network into natural language processing to do the task of text classification.…”