Optimization of Deep Learning Models for Dynamic Market Behavior Prediction

A recent study has demonstrated the effectiveness of spatiotemporal Graph Neural Networks (GNNs) in forecasting multi-store retail sales, specifically using data from 45 Walmart locations. The research highlights the STGNN's ability to model inter-store dependencies and achieve lower forecasting errors compared to traditional methods like ARIMA, LSTM, and XGBoost.

A new framework for Electric Vehicle (EV) charging forecasting has been proposed, addressing cybersecurity threats that compromise operational efficiency and grid stability. This framework employs a federated learning approach that integrates LSTM autoencoder-based anomaly detection, interpolation for data mitigation, and collaborative learning without centralized data aggregation.

A recent study compared the performance of Kolmogorov-Arnold Networks (KAN) and Long Short-Term Memory (LSTM) networks in forecasting non-deterministic stock price data. The findings revealed that LSTM outperformed KAN across all tested prediction horizons, demonstrating its effectiveness in sequential data modeling while KAN showed higher error rates despite its theoretical interpretability.

A new dataset named MultiBanAbs has been developed to facilitate Bangla abstractive summarization, comprising over 54,000 articles and summaries from diverse sources including blogs and newspapers. This initiative addresses the limitations of existing summarization systems that primarily focus on news articles, which often do not reflect the varied nature of real-world Bangla texts.

Recent research has introduced Liquid Time-Constant Networks (LTCs) and Closed-form Continuous-time Networks (CfCs) to model retinal ganglion cell activity in tiger salamanders, demonstrating lower mean absolute error (MAE) and faster convergence compared to traditional convolutional models and LSTMs.

A recent study has introduced a bidirectional Long Short-Term Memory (LSTM) neural network designed to classify light curves of transient astronomical objects using data from the Photometric LSST Astronomical Time-series Classification Challenge (PLAsTiCC). The study reorganized the original fourteen object classes into five categories to mitigate class imbalance, achieving high performance in certain classifications while facing challenges with others.

A new paper presents a hybrid framework for portfolio optimization that combines Long Short-Term Memory (LSTM) forecasting with Proximal Policy Optimization (PPO) reinforcement learning. This innovative approach aims to enhance portfolio management by leveraging deep learning to predict market trends and dynamically adjust asset allocations across various financial instruments, including U.S. and Indonesian equities, U.S. Treasuries, and cryptocurrencies.

A recent study published on arXiv systematically evaluated 12 feature scaling techniques across 14 machine learning algorithms and 16 datasets, revealing significant performance variations in models like Logistic Regression and SVMs, while ensemble methods showed robustness regardless of scaling.