Marcos Costa Santos Carreira

Yes, but adding it to the conda environment makes it easier to check for upgrades and it would reach a wider base of users if it became part of the...

A simple way to find the best decay in the original question: from scipy.optimize import minimize def find_decay(timestamps, decays_init): def min_hawkes_sum_exp(decays_init): return -HawkesSumExpKern(decays_init, solver='bfgs')\ .fit(timestamps).score() return minimize(min_hawkes_sum_exp, decays_init, method='Nelder-Mead', options={'disp':...

I had collision problems on financial time series (mainly on ms timestamps), so I: 1. Calculated the max number of down in same timestamp (e.g. 21) 2. Subtract 1/2 of...

I think that from NNT's point of view is to think about fat-tailed distributions as your prior, since it takes a lot of data to disprove it, while disproving a...

A clear example is attached: [NeedForLatency.pdf](https://github.com/X-DataInitiative/tick/files/4973878/NeedForLatency.pdf)

Addressed in the paper "Exponential Kernels with Latency in Hawkes Processes: Applications in Finance" [https://arxiv.org/abs/2101.06348](url)