zeki-kadiroglu / Demand_prediction_TimeSeries_LSTM

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

#Bike Share -In this project, the goal is to predict the number of future bike shares given the historical data of London bike shares.

-So this case should be handled as a time series problem with Bidirectional LSTM.

-In order to achieve this goal, you will make predictions with LSTM, unlike the machine learning algorithms you have applied before.

-Long short term memory (LSTM) is an artificial repetitive neural network architecture used in the field of deep learning.

-Unlike standard feed forward neural networks, LSTM has feedback links. It can process not only single data points but also entire data series.

dataset: alt text

cnt distribution: alt text

change over the time : alt text

loss function result after bidirectionalLSTM algorithm: alt text

Time Series plot for actual and prediction: alt text

our pattern after deep learning algoritm: alt text

About


Languages

Language:Jupyter Notebook 100.0%