HighFrequencyEconometrics-HAR-vs.-Neural-Networks
Unverified ML strategy on Indices by RasLillebo. BotFinder score 18 out of 100.
Inspired by Hillebrand & Medeiros (2009) and Corsi (2009), I put neural networks in a High frequency environment, and tested the performance of the two models (HAR & Neural Network
Source: github
BotFinder analysis pending.
HighFrequencyEconometrics-HAR-vs.-Neural-Networks
High Frequency Econometrics: HAR vs. Neural-Networks (Disclaimer: High Frequency Econometrics, High Frequency data manipulation, HAR, Neural Networks, Bagging, Cross-validation, Bayesian Ensemble) Inspired by Hillebrand & Medeiros (2009) and Corsi (2009), I put neural networks in a High frequency environment, and tested the performance of the two models (HAR & Neural Networks). - The data used in this project is 2 years worth of intraday 5-minute realized volatility (See: Sheppard, Patton, Liu, 2012) from S&P500 stocks, that has been scrutinized using bivariate analysis and manipulation into a single dimension. Introduction to the models: HAR (Heterogenous Autoregressive model): Developed by Corsi in 2009, this model is based on a simple regression framework. The independent variables are simply the daily volatility lagged 1, 5 and 22 days respectively. This is to simulate the volatility of yesterday, a week ago, and approximately one month ago (Only taking open market days into account). This type of model is also called a 'Long memory'-model, as it "remembers" what happened
⚠ No verified equity curve — no track-record source connected.
Drawdown profile
Data unavailable — contact the owner.
Verification ledger
How the score has moved
Recalculated at each data collection. Transparency means showing the bad weeks too.
No score history is stored yet — only the current score is shown.
Reviews & comments
No reviews collected from the source yet.
⚠ No live verification account connected — ask for proof before buying.
Alerts on changes: coming soon
Prop-firm compatibility not provided.
Open-source maintainer on GitHub.
Data-completeness & trust index (not a profitability rating)