Hi Rob,
Inspired by your position in the Mothers Index as revealed on a recent podcast I got the dynamic optimisation running locally. My dataset is a bit rough in places, the code to robustly download hourly prices for 120 markets using IBs API is a test of nerve and patience. These are my recent positions, the data for BBCOMM is stale.
Looking at the equity curve there are some strange spikes which need investigating, again it's probably my underlying data (data is bootstrapped from various places).
It is interesting that given this broad universe this is what DO chooses to allocate risk to.
Given your experience with DO so far, where do you think you would focus further research? On my TODO is to dig deeper and pull out the covariance clusters from which we've picked the above. Nice!
How are you collecting data for these 100+ markets? Do you batch download hourly, or do you just grad daily prices? I guess you have a realtime thing running to monitor moves?
Inspired by your position in the Mothers Index as revealed on a recent podcast I got the dynamic optimisation running locally. My dataset is a bit rough in places, the code to robustly download hourly prices for 120 markets using IBs API is a test of nerve and patience. These are my recent positions, the data for BBCOMM is stale.
Code:
BBCOMM BITCOIN CORN CRUDE_W_mini V2X VIX
index
2022-01-06 3.0 0.0 0.0 0.0 -2.0 -1.0
2022-01-07 3.0 0.0 0.0 0.0 -2.0 -1.0
2022-01-10 3.0 -1.0 0.0 0.0 -2.0 -1.0
2022-01-11 3.0 -1.0 0.0 0.0 -2.0 -1.0
2022-01-12 3.0 -1.0 1.0 0.0 -2.0 -1.0
2022-01-13 3.0 -1.0 1.0 0.0 -2.0 -1.0
2022-01-14 3.0 -1.0 1.0 0.0 -2.0 -1.0
2022-01-17 0.0 -1.0 1.0 0.0 -2.0 -1.0
2022-01-18 0.0 -1.0 1.0 1.0 -2.0 -1.0
2022-01-19 0.0 -1.0 1.0 1.0 -2.0 -1.0
Looking at the equity curve there are some strange spikes which need investigating, again it's probably my underlying data (data is bootstrapped from various places).
It is interesting that given this broad universe this is what DO chooses to allocate risk to.
Given your experience with DO so far, where do you think you would focus further research? On my TODO is to dig deeper and pull out the covariance clusters from which we've picked the above. Nice!
How are you collecting data for these 100+ markets? Do you batch download hourly, or do you just grad daily prices? I guess you have a realtime thing running to monitor moves?
Last edited:
probably lost 3% or so..