See the previous installment in this series for Setup and Download.
Below is a peak into what that data looks like. You can get results directly from the returned
Scan() object but I prefer to read back the csv and analyze that since I’d like to be able to monitor results as the come in (different process) and be able to evaluate in future w/o re-running the Scan.
Note: Since Log-Loss values are all so tightly distributed, I’m creating a vallossimprovement metric which is the improvement relative to naive baseline (always estimating 50% probability). For this metric, higher is better.
We could simply take the top result and call it good. However, I think the real value here is to gain understanding about how parameters affect results. Further it’s very unlikely that we’ve happened to find the global maximum with our starting values.
Below, I’ll start by running several univariate measures to see what the impact of each factor appears to be, in isolation:
As a total aside, we can also measure relationships which all assume, but may not know for certain. Below, I’ve plotted the number of epochs before early stopping (when the model begins to overfit and get worse on validation) vs. network size. Unsurprisingly, it takes larger networks longer to converge. The relationship seems pretty close to logarithmic relative to “links” between nodes.In :
Visit The Alpha Scientist blog to download the complete code:
The Alpha Scientist blog – Chad is a full-time quantitative trader who has been working on data analytics since before it was cool. He has long balanced his interest in computer science (MS in EE/CS from MIT) with a fascination in markets (CFA designation in 2009). Prior to becoming a full-time quant, he built analytics products and managed teams at software companies across Silicon Valley. If you’ve found this post useful, please follow @data2alpha on Twitter and forward to a friend or colleague who may also find this topic interesting. https://alphascientist.com/
Disclosure: Interactive Brokers
Information posted on IBKR Traders’ Insight that is provided by third-parties and not by Interactive Brokers does NOT constitute a recommendation by Interactive Brokers that you should contract for the services of that third party. Third-party participants who contribute to IBKR Traders’ Insight are independent of Interactive Brokers and Interactive Brokers does not make any representations or warranties concerning the services offered, their past or future performance, or the accuracy of the information provided by the third party. Past performance is no guarantee of future results.
This material is from The Alpha Scientist and is being posted with permission from The Alpha Scientist. The views expressed in this material are solely those of the author and/or The Alpha Scientist and IBKR is not endorsing or recommending any investment or trading discussed in the material. This material is not and should not be construed as an offer to sell or the solicitation of an offer to buy any security. To the extent that this material discusses general market activity, industry or sector trends or other broad based economic or political conditions, it should not be construed as research or investment advice. To the extent that it includes references to specific securities, commodities, currencies, or other instruments, those references do not constitute a recommendation to buy, sell or hold such security. This material does not and is not intended to take into account the particular financial conditions, investment objectives or requirements of individual customers. Before acting on this material, you should consider whether it is suitable for your particular circumstances and, as necessary, seek professional advice.