I wish the diagrams were bigger, they are hard to read and a bit blurry.<p>One of the interesting points, that is often overlooked in ML is model deployment. They mention tensorflow, which has a model export feature that you can use as long as your client can run the tensorflow runtime. But they don't seem to be using that b/c they said they just exported the weights and are using it go which would seem to imply you did some type of agnostic export of raw weight values. The nice part of the TF export feature is that it can be used to recreate your architecture on the client. Bu they did mention Keras too which allows you to export your architecture in a more agnostic way as it can work on many platform such as Apples new CoreML which can run Keras models.
I wonder how much they could enlist others to solve this by creating something like an 'Uber Auction House' to basically buy and sell the right to reap Uber's cut for a ride. They could clean up on exchange fees while everyone solves this problem for them.
I don't understand if they use windowing as a fixed computational step that is active both in training and scoring time, or, if they use sliding windows only to chop up the training data.<p>Also, I wonder if they checked how a feed-forward NN that operates on the contents of a sliding window (e.g. as in the first approach above) compares with their RNN results. I am curious about this, as it would give us a hint whether the RNN's internal state encodes something that is not a simple transformation of the window contents. If this turns out to be the case, I'd then be interested in figuring out what the internal state "means"; i.e. whether there is anything there that we humans can recognize.<p>[edited to increase clarity]
Whenever I see a post or announcement by a major company that they're using "machine learning", I'm reminded of what CGP Grey said: it seems like nowadays machine learning is something you add in to your product just so you can seem hip by saying that it has machine learning, and not for a legitimate technical reason.<p>There are undoubtedly things that machine learning is right for, however to me it seems like it's become a buzzword more than anything else.
Interesting stuff, but all they've managed to do so far is find models that fit historical data better. Would be interested to read a follow up a year later to see how their models actually performed.
I wonder how are they quantifying uncertainty around their predictions. Having a point-estimate without some notion of confidence interval seems much less useful. Is there a natural way to do this through LSTMs?<p>Also, some actual benchmarking would be great. Say, against Facebook's Prophet (which also deals with covariates and holiday effects).