Salma Albelali

Salma Albelali, Moataz Ahmed

Deep learning models, particularly Long Short-Term Memory (LSTM) networks, are widely used in time series forecasting due to their ability to capture complex temporal dependencies. However, evaluation integrity is often compromised by data leakage, a methodological flaw in which input-output sequences are constructed before dataset partitioning, allowing future information to unintentionally influence training. This study investigates the impact of data leakage on performance, focusing on how validation design mediates leakage sensitivity. Three widely used validation techniques (2-way split, 3-way split, and 10-fold cross-validation) are evaluated under both leaky (pre-split sequence generation) and clean conditions, with the latter mitigating leakage risk by enforcing temporal separation during data splitting prior to sequence construction. The effect of leakage is assessed using RMSE Gain, which measures the relative increase in RMSE caused by leakage, computed as the percentage difference between leaky and clean setups. Empirical results show that 10-fold cross-validation exhibits RMSE Gain values of up to 20.5% at extended lag steps. In contrast, 2-way and 3-way splits demonstrate greater robustness, typically maintaining RMSE Gain below 5% across diverse configurations. Moreover, input window size and lag step significantly influence leakage sensitivity: smaller windows and longer lags increase the risk of leakage, whereas larger windows help reduce it. These findings underscore the need for configuration-aware, leakage-resistant evaluation pipelines to ensure reliable performance estimation.

Salma Albelali, Moataz Ahmed

Deep learning (DL) models, a specialized class of multilayer neural networks, have become central to time-series forecasting in critical domains such as environmental monitoring and the Internet of Things (IoT). Among these, Bidirectional Long Short-Term Memory (BiLSTM) architectures are particularly effective in capturing complex temporal dependencies. However, the robustness and generalization of such models are highly sensitive to input data characteristics - an aspect that remains underexplored in existing literature. This study presents a systematic empirical analysis of two key data-centric factors: input sequence length and additive noise. To support this investigation, a modular and reproducible forecasting pipeline is developed, incorporating standardized preprocessing, sequence generation, model training, validation, and evaluation. Controlled experiments are conducted on three real-world datasets with varying sampling frequencies to assess BiLSTM performance under different input conditions. The results yield three key findings: (1) longer input sequences significantly increase the risk of overfitting and data leakage, particularly in data-constrained environments; (2) additive noise consistently degrades predictive accuracy across sampling frequencies; and (3) the simultaneous presence of both factors results in the most substantial decline in model stability. While datasets with higher observation frequencies exhibit greater robustness, they remain vulnerable when both input challenges are present. These findings highlight important limitations in current DL-based forecasting pipelines and underscore the need for data-aware design strategies. This work contributes to a deeper understanding of DL model behavior in dynamic time-series environments and provides practical insights for developing more reliable and generalizable forecasting systems.