The paper focuses on predicting the next purchase day (NPD) for customers in e-commerce, a task with applications in marketing, inventory management, and customer retention. A novel transformer-based model for NPD prediction is introduced and compared to traditional methods such as ARIMA, XGBoost, and LSTM. Transformers offer advantages in capturing long-term dependencies within time series data through self-attention mechanisms. This adaptability to various time series patterns, including trends, seasonality, and irregularities, makes them a promising choice for NPD prediction. The transformer model demonstrates improvements in prediction accuracy compared to the baselines. Additionally, a clustered transformer model is proposed, which further enhances accuracy, emphasizing the potential of this architecture for NPD prediction.

A model for generating synthetic time series data using pre-trained large language models is proposed. Starting with the Google T5-base model, which employs an encoder–decoder transformer architecture, the model underwent pre-training on diverse datasets. It was then fine-tuned using the QLoRA technique, which reduces computational complexity by quantizing weight parameters. The process involves the tokenization of time series data through mean scaling and quantization. The performance of the model was evaluated with fidelity, utility, and privacy metrics, showing improvements in fidelity and utility but a trade-off with reduced privacy. The proposed model offers a foundation for decision intelligence systems.