Çağatay Demirel

Çağatay Demirel, A. Aylin Tokuç, Ahmet Tezcan Tekin

Online travel agencies (OTA's) advertise their website offers on meta-search bidding engines. The problem of predicting the number of clicks a hotel would receive for a given bid amount is an important step in the management of an OTA's advertisement campaign on a meta-search engine, because bid times number of clicks defines the cost to be generated. Various regressors are ensembled in this work to improve click prediction performance. Following the preprocessing procedures, the feature set is divided into train and test groups depending on the logging date of the samples. The data collection is then subjected to feature elimination via utilizing XGBoost, which significantly reduces the dimension of features. The optimum hyper-parameters are then found by applying Bayesian hyperparameter optimization to XGBoost, LightGBM, and SGD models. The different trained models are tested separately as well as combined to form ensemble models. Four alternative ensemble solutions have been suggested. The same test set is used to test both individual and ensemble models, and the results of 46 model combinations demonstrate that stack ensemble models yield the desired R2 score of all. In conclusion, the ensemble model improves the prediction performance by about 10%.

Çağatay Demirel

Ensemble learning remains a cornerstone of machine learning, with stacking used to integrate predictions from multiple base learners through a meta-model. However, deep stacking remains rare, as most designs prioritize horizontal diversity over recursive depth due to model complexity, feature redundancy, and computational burden. To address these challenges, RocketStack, a level-aware recursive ensemble framework, is introduced and explored up to ten stacking levels, extending beyond prior architectures. The framework incrementally prunes weaker learners at each level, enabling deeper stacking without excessive complexity. To mitigate early performance saturation, mild Gaussian noise is added to out-of-fold (OOF) scores before pruning, and compared against strict OOF pruning. Further both per-level and periodic feature compressions are explored using attention-based selection, Simple, Fast, Efficient (SFE) filter, and autoencoders. Across 33 datasets (23 binary, 10 multi-class), linear-trend tests confirmed rising accuracy with depth in most variants, and the top performing meta-model at each level increasingly outperformed the strongest standalone ensemble. In the binary subset, periodic SFE with mild OOF-score randomization reached 97.08% at level 10, 5.14% above the strict-pruning configuration and cut runtime by 10.5% relative to no compression. In the multi-class subset, periodic attention selection reached 98.60% at level 10, exceeding the strongest baseline by 6.11%, while reducing runtime by 56.1% and feature dimensionality by 74% compared to no compression. These findings highlight mild randomization as an effective regularizer and periodic compression as a stabilizer. Echoing the design of multistage rockets in aerospace (prune, compress, propel) RocketStack achieves deep recursive ensembling with tractable complexity.