Handling frequency in machine learning One of the trickiest situations in machine learning is when you have to deal with datasets coming from different time scales. Let’s say, for example, that you are handling financial data, and some of the data is collected monthly (e.g. sales reports), and some other data comes at a daily frequency (e.g. stock market prices). How can you create a model that utilizes both pieces of information at the same time? One solution is to try and create aggregates of the higher frequency features. So, for example, in this case, you can aggregate the daily frequency features on a monthly level using functions like the mean, and the . However, this makes you use lose information, and it might be a suboptimal solution. standard deviation A better solution can arrive through the use of . deep learning Deep learning for handling data with different frequency Using deep neural networks it is possible to do this vert smoothly. You can create two subnetworks: one network reads the daily data, and the other network reads the monthly data. The outputs of the two subnetworks are then joined together before they are passed into another layer. The code below shows how you could do this for the two datasets we outlined above. import pandas as pd from tensorflow import keras from tensorflow.keras import layers from tensorflow.keras.layers import X_day=pd.read_csv('day_data.csv') X_month=pd.read_csv('month_data.csv')
day_input = keras.Input(shape=day_X.shape[1:3], name="day_input")
monthly_input = keras.Input(shape=month_X.shape[1], name="monthly_input")
x1 = LSTM(50)(day_input)
x2 = Dense(num_units,activation='elu')(monthly_input)
merging=Concatenate()([x1,x2])
x = Dense(100,activation='elu')(merging) x = BatchNormalization()(x) 
x = Dropout(0.2)(x) y = Dense(3,'softmax')(x) The benefit of using deep learning The benefit of using deep learning, in this case, is that you are not losing any information which would have been lost otherwise by aggregating features together. This is done through the use of a layer, like or , which can read sequential data. We are simply using a dense layer for the monthly data (processing each month in one batch), and then we can merge the two subnetworks together. LSTM, GRU 1d convolution So, make sure to check this trick out next time you are faced with this problem! Also published here.

This story contains new, firsthand information uncovered by the writer.

Different

Shaping the Future of Entertainment: Web3.0 and Play-to-Earn Games

Merging Datasets from Different Timescales

About Author

Comments

TOPICS

THIS ARTICLE WAS FEATURED IN

Related Stories

3 Types of Anomalies in Anomaly Detection

The Noonification: How Often Do NFTs Pass The Howey Test? (1/13/2023)

03/09/2018: Biggest Stories in the Cryptosphere

The Noonification: Immigrant Teens Are Working Dangerous Night Shifts in Factories (11/21/2022)

The Noonification: How to Implement a Merkle Tree in Solidity (11/12/2023)

10 Ways to Optimize Your Database

3 Types of Anomalies in Anomaly Detection

The Noonification: How Often Do NFTs Pass The Howey Test? (1/13/2023)

03/09/2018: Biggest Stories in the Cryptosphere

The Noonification: Immigrant Teens Are Working Dangerous Night Shifts in Factories (11/21/2022)

The Noonification: How to Implement a Merkle Tree in Solidity (11/12/2023)

10 Ways to Optimize Your Database

Light-Mode

Classic

Newspaper

Minty

Dark-Mode

Neon Noir

Minty

HN StartUps