Too Long; Didn't Read
Using deep neural networks it is possible to do this in a smooth manner. You can create two subnetworks: one network reads the daily data, the other network reads monthly data. The outputs of the two networks are then joined together, before they are passed in another layer. This is done through the use of a layer, like [LSTM] or [1d convolution/layers/convolution_layers] The code below shows how you could do this for the two datasets outlined above.