Explore the vast range of titles available.

Deep learning models struggle to effectively capture data features and make accurate predictions because of the strong non-linear characteristics of arbitrage data. Therefore, to fully exploit the model performance, researchers have focused on network structure and hyperparameter selection using various swarm intelligence algorithms for optimization. Sparrow Search Algorithm (SSA), a classic heuristic method that simulates the sparrows’ foraging and anti-predatory behavior, has demonstrated excellent performance in various optimization problems. Hence, in this study, the Multi-Strategy Modified Sparrow Search Algorithm (MSMSSA) is applied to the Long Short-Term Memory (LSTM) network to construct an arbitrage spread prediction model (MSMSSA-LSTM). In the modified algorithm, the good point set theory, the proportion-adaptive strategy, and the improved location update method are introduced to further enhance the spatial exploration capability of the sparrow. The proposed model was evaluated using the real spread data of rebar and hot coil futures in the Chinese futures market. The obtained results showed that the mean absolute percentage error, root mean square error, and mean absolute error of the proposed model had decreased by a maximum of 58.5%, 65.2%, and 67.6% compared to several classical models. The model has high accuracy in predicting arbitrage spreads, which can provide some reference for investors.

Due to its effectiveness as a risk-hedging trading strategy in financial markets, futures arbitrage is highly sought after by investors in turbulent market conditions. The essence of futures arbitrage lies in formulating strategies based on predictions of future futures price differentials. However, contemporary research predominantly focuses on projections of single indicators for the subsequent temporal juncture, and devising efficacious arbitrage strategies often necessitates the examination of multiple indicators across timeframes. To tackle the aforementioned challenge, our methodology leverages a PSO Deep-ConvLSTM network, which, through particle swarm optimization (PSO), refines hyperparameters, including layer architectures and learning rates, culminating in superior predictive performance. By analyzing temporal-spatial data within financial markets through ConvLSTM, the model captures intricate market patterns, performing better in forecasting than traditional models. Multistep forward simulation experiments and extensive ablation studies using future data from the Shanghai Futures Exchange in China validate the effectiveness of the integrated model. Compared with the gate recurrent unit (GRU), long short-term memory (LSTM), Transformer, and FEDformer, this model exhibits an average reduction of 39.8% in root mean squared error (RMSE), 42.5% in mean absolute error (MAE), 45.6% in mean absolute percentage error (MAPE), and an average increase of 1.96% in coefficient of determination (R2) values.

Arbitrage spread prediction can provide valuable insights into the identification of arbitrage signals and assessing associated risks in algorithmic trading. However, achieving precise forecasts by increasing model complexity remains a challenging task. Moreover, uncertainty in the development and maintenance of model often results in extremely unstable returns. To address these challenges, we propose a K-fold cross-search algorithm-optimized LSTM (KCS-LSTM) network for arbitrage spread prediction. The KCS heuristic algorithm incorporates an iterative updating mechanism of the search space with intervals as the basic unit into the traditional ant colony optimization. It optimized the hyperparameters of the LSTM model with a modified fitness function to automatically adapt to various data sets, thereby simplified and enhanced the efficiency of model development. The KCS-LSTM network was validated using real spread data of rebar and hot-rolled coil from the past three years. The results demonstrate that the proposed model outperforms several common models on sMAPE by improving up to 12.6% to 72.4%. The KCS-LSTM network is shown to be competitive in predicting arbitrage spreads compared to complex neural network models.

Particle sedimentation has widely existed in nature and engineering fields, and most carrier fluids are non-Newtonian. Recently, the manipulation of a settling particle in liquid has been a topic of high interest to those involved in engineered processes such as composite materials, pharmaceutical manufacture, chemistry and the petroleum industry. Compared with Newtonian fluid, the viscosity of non-Newtonian fluid is closely related to the shear rate, leading to a single settling particle having different dynamic behaviors. In this article, the trajectories and velocities of two side-by-side particles of different densities (heavy and light) settling in a shear-thinning fluid with viscoelastic property were studied, as well as that for the corresponding single settling particle. Regardless of the difference in the particle density, the results show the two-way coupling interaction between the two side-by-side settling particles. As opposed to a single settling particle, the wake of the heavier particle can clearly attract or rebound the light particle due to the shear-thinning or viscoelastic property of the fluid. Regarding the trajectories of the light particle, three basic path types were found: (i) the light particle is first attracted and then repelled by the wake of the heavy one; (ii) the light particle approaches and then largely traces within the path of the heavy one in the limited field of view; (iii) the light particle is first slightly shifted away from its original position and then returns to this initial position. In addition to this, due to the existence of a corridor of reduced viscosity and negative wake generated by the viscoelastic property, the settling velocity of a light particle can exceed the terminal velocity of a single particle of the same density. On the other hand, the sedimentation of the light particle can induce the distinguishable transverse migration of the heavy one.

Although the bubble contacting a uniformly superaerophilic surface has caused concern due to its application potential in various engineering equipment, such as mineral flotation, very little is known about the mechanism of how the bubble spreads on a surface with anisotropic superaerophilicity. To unveil this mystery, we experimentally studied the anisotropic behavior of a bubble (2 mm in diameter) spreading on the superaerophilic straight trajectories (SALTs) of different widths (0.5 mm–5 mm) in water using a high-speed shadowgraphy system. The 1–3 bounces mostly happened as the bubble approached the SALTs before its spreading. It is first observed that the bubble would be split into two highly symmetrical sub-bubbles with similar migration velocity in opposite directions during the anisotropic spreading. Two essential mechanisms are found to be responsible for the anisotropic spreading on the narrow SALTs (W ≤ 2 mm with two subregimes) and the wide SALTs (W ≥ 3 mm with four subregimes). Considering the combined effect of the surface tension effect of SALT and Laplace pressure, a novel model has been developed to predict the contact size r(t) as a function of time. The nice agreement between this model and our experiments reconfirms that the surface tension effect and Laplace pressure prevail over the hydrostatic pressure.