Researchers have developed NeuroMem-FHP, a deep learning framework designed to estimate parameters for the fractional Hawkes process (FHP). This framework utilizes Long Short-Term Memory (LSTM) and Transformer neural networks to directly infer model parameters from inter-arrival time sequences, bypassing computationally intensive likelihood optimization. Experiments show that the Transformer model achieves superior accuracy compared to LSTM and traditional Maximum Likelihood Estimation (MLE) on both synthetic and real-world datasets, including financial transaction data from Apple Inc. and emergency call records from Montgomery County. AI
IMPACT Offers a more accurate and efficient alternative to traditional methods for modeling event-driven systems with long-memory dynamics.
RANK_REASON The cluster contains an academic paper detailing a new deep learning framework for parameter estimation.
- Aditya Maheshwari
- Apple Inc.
- Fractional Hawkes Process
- long short-term memory
- maximum likelihood estimation
- Montgomery County
- NeuroMem-FHP
- Transformer
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
