23.06.2021 - Hong Kong Machine Learning - ~2 Minutes
- Wednesday, June 23, 2021 from 7:00 PM to 9:00 PM (Hong Kong Time)
- At your home, on zoom. All meetups will be online as long as this COVID-19 crisis is not over.
Talk 1: The Book of Alternative Data: A Guide for Investors, Traders and Risk Managers
Talk 2: Hawkes Processes and Market Microstructure: Too fast but not even furious
How do we reconcile the mathematics of continuous process like diffusion to the discrete observed prices? Is it always possible? In this talk we show how an improved version of the Uncertainty Zones model by Robert and Rosenbaum can explain most of the price changes on normal days. Then we introduce Multivariate Hawkes Processes (with latency) to explain the fast dynamics of the order book and conclude by discussing what happens when the different decision functions of slow and fast agents become very similar.
Talk 3: FinBERT: A Pretrained Language Model for Financial Communications
Contextual pretrained language models, such as BERT (Devlin et al., 2019), have made significant breakthrough in various NLP tasks by training on large scale of unlabeled text re-sources.Financial sector also accumulates large amount of financial communication text.However, there is no pretrained finance specific language models available. In this work,we address the need by pretraining a financial domain specific BERT models, FinBERT, using a large scale of financial communication corpora. Experiments on three financial sentiment classification tasks confirm the advantage of FinBERT over generic domain BERT model. The code and pretrained models are available at this https URL. We hope this will be useful for practitioners and researchers working on financial NLP tasks.
Video Recording of the HKML Meetup on YouTube
- YouTube videos:
Thanks to our patrons for supporting the meetup!
Check the patreon page to join the current list: