Markus K.
Markus K.
[https://breakingdownfinance.com/finance-topics/performance-measurement/m2-measure/](https://breakingdownfinance.com/finance-topics/performance-measurement/m2-measure/) [https://breakingdownfinance.com/finance-topics/performance-measurement/treynor-ratio/](https://breakingdownfinance.com/finance-topics/performance-measurement/treynor-ratio/) [https://breakingdownfinance.com/finance-topics/performance-measurement/jensens-alpha/](https://breakingdownfinance.com/finance-topics/performance-measurement/jensens-alpha/) Stumbled upon those ratios and thought it might be interesting for quantstats.
The metrics are rounded to 2 decimals by default. For some use-cases, it might be good to have the exact value and if needed do the rounding just if needed...
``` root@1536b88504d4:/home/live# pip install --upgrade timemachines Collecting timemachines Downloading timemachines-0.14.7-py3-none-any.whl (139 kB) |████████████████████████████████| 139 kB 2.6 MB/s Collecting microconventions>=0.5.1 Downloading microconventions-0.5.1-py3-none-any.whl (15 kB) Collecting momentum>=0.2.1 Downloading momentum-0.2.1-py3-none-any.whl (6.8 kB) Requirement...
``` xi, x_std, self.s = self.skater(y=round(yi, 6), s=self.s, k=1) File "/usr/local/lib/python3.9/site-packages/timemachines/skaters/smdk/smdkarma.py", line 21, in smdk_p5_d0_q3_n500_aggressive return smdk_arma_factory(y=y, n_agents=500, max_p=5, max_q=3, s=s, k=k, a=a, t=t, e=e, r=0.95) File "/usr/local/lib/python3.9/site-packages/timemachines/skaters/smdk/smdkarmafactory.py", line 119,...
_"Traditional time-based candlesticks are an inefficient method to aggregate price data, especially under two situations: (a) highly volatile markets such as cryptocurrencies and (b) when using algorithmic or automatic trading."_...
Adding normalization to the data preprocessor might be a great feature: - Min-Max Normalization, - Decimal Scaling Normalization, - Z-Score Normalization, - Median Normalization, - Sigmoid Normalization, - Tanh estimators...
**Candle information** (might help the model learning candlestick patterns): - hl2 Price - hlc3 Price - ohlc4 Price ``` def upper_shadow(df): return df['High'] - np.maximum(df['Close'], df['Open']) def lower_shadow(df): return np.minimum(df['Close'],...
It's really important to not overlook the reward part. Just using return is probably the reason most fail with RL. This might be far more essential than the agents: _"The...
After some more exploring, one thing I realized is, that plotting (with pyfolio / quantstats) to evaluate the results is harder than it needs to be. Currently we have no...
A great repo and paper: [https://github.com/golsun/deep-RL-trading](https://github.com/golsun/deep-RL-trading) This could be useful for FinRL maybe as helper / environment function. Training first on rather simple idealized synthetic prices before feeding real data...