Predicting asset price trends is often posed as a classification problem, where trends are classified as positive or negative. Since asset price series are noisy and volatile, it is difficult to distinguish true trends from short-term fluctuations. To this end, several trend definitions have been proposed in the literature, but it is yet to be known how these trend definitions affect the performance of classification algorithms designed to learn such labels from historical data. In this paper, we define the robustness of the trend labeling algorithm as a measure of how well a classifier designed to learn such labels can withstand a change in the cumulative return considering the classifier’s generalization error. Moreover, we propose a noise model to simulate the desired accuracy score, which allows us to evaluate the robustness of a trend labeling algorithm without the need to train an actual classifier and consequently choose the optimal algorithm in terms of robustness. Experimental results confirm the adequacy of the proposed noise model and show that classification algorithms perform better when trained with such optimal labels.

Pure titanium (Ti) and its alloys are the gold standard for dental implants because a stable titanium dioxide passive film provides excellent corrosion resistance in physiological environments. In this study, we aimed to examine electrochemical interactions between Ti and cobalt–chromium–molybdenum alloy (CoCrMo), and between a novel Ti–magnesium composite (BIACOM TiMg) and CoCrMo, when immersed in everyday solutions representing beverage or oral hygiene exposure. Test solutions included Coca-Cola^®, lemon juice, Elmex^® fluoride gel, Listerine^® Cool Mint, and Sensodyne^® fluoride paste. Immersion experiments paired Ti sticks with CoCrMo sticks and, separately, BIACOM TiMg with CoCrMo sticks, with three measurements per configuration. When galvanically coupled with CoCrMo, immersion in Coca-Cola produced galvanic potential differences of ~983 mV for the BIACOM TiMg-CoCrMo couple and 830 mV for the commercially pure grade 4 (CP4) Ti-CoCrMo couple, indicating significant electrochemical instability. Both materials showed significant potential increases in Elmex fluoride gel. Listerine Cool Mint and Sensodyne fluoride exposure produced electrochemical interactions exceeding 200 mV. Significant differences in corrosion stability were observed between CP4 Ti and BIACOM TiMg. These findings indicate that material pairing and electrolyte environment significantly influence galvanic behavior, with the Ti-Mg composite showing greater susceptibility than CP4 Ti, informing dental/biomedical material selection in oral environments.

Pure titanium (Ti) and its alloys are the "gold standard" for dental implants due to their stable titanium dioxide passive film providing excellent corrosion resistance in physiological environments. This study examined electrochemical interactions between Ti and cobalt-chromium-molybdenum alloy (CoCrMo), and between a novel Ti-Magnesium composite (BIACOM TiMg) and CoCrMo, when immersed in everyday solutions representing beverage or oral hygiene exposure. Test solutions included Coca-Cola®, lemon juice, Elmex® fluoride gel, Listerine® Cool Mint, and Sensodyne® fluoride paste. The immersion experiment paired Ti sticks with CoCrMo sticks, then BIACOM TiMg composite with CoCrMo sticks, with three measurements per configuration. Coca-Cola immersion increased electrochemical potential to ~983 mV for BIACOM TiMg and ~830 mV for CP4 titanium. Significant potential increases occurred in Elmex fluoride gel for both materials. Listerine Cool Mint and Sensodyne Fluoride exposures showed electrochemical interactions exceeding 200 mV. Marked differences in corrosion stability between CP4 titanium and BIACOM TiMg composite were confirmed. Findings indicate that material pairing and electrolyte environment significantly influence galvanic and corrosion behavior, with Ti-Mg composite showing higher susceptibility than CP4 titanium under tested conditions, impacting dental/biomedical material selection in oral environments.

The sequential nature of decision-making in financial asset trading aligns naturally with the reinforcement learning (RL) framework, making RL a common approach in this domain. However, the low signal-to-noise ratio in financial markets results in noisy estimates of environment components, including the reward function, which hinders effective policy learning by RL agents. Given the critical importance of reward function design in RL problems, this paper introduces a novel and more robust reward function by leveraging imitation learning, where a trend labeling algorithm acts as an expert. We integrate imitation (expert's) feedback with reinforcement (agent's) feedback in a model-free RL algorithm, effectively embedding the imitation learning problem within the RL paradigm to handle the stochasticity of reward signals. Empirical results demonstrate that this novel approach improves financial performance metrics compared to traditional benchmarks and RL agents trained solely using reinforcement feedback.