Page 9 - Azerbaijan State University of Economics

Hadouga. H: Prediction Of Agricultural Growth Rate As A Result Of Agricultural Reforms

where s and j are the splitting point and variables, respectively. Further, s and j are
used for achieving the most uniform splitting group.
The embedding formulation in (Atkeson,1997).suggests that, once a historical record
S is available, the problem of one-step forecasting can be tackled as a problem of
supervised learning. Supervised learning consists in modeling, on the basis of a
finite set of observations, the relation between a set of input variables and one or
more output variables, which are considered somewhat dependent on the inputs.
Once a model of the mapping is available, it can be used for one-step forecasting.
In one-step forecasting, the n previous values of the series are available and the
forecasting problem can be cast in the form of a generic regression problem.

A multi-step time series forecasting task consists of predicting the next H
values [yN+1,... , yN+H ] of a historical time series [y 1,..., yN ] composed of N
observations, where H > 1 denotes the forecasting horizon. (Casdagli, 1991)

The Recursive strategy (Sorjamaa, ,2007) trains first a one-step model f

yt+1 = f (yt,... , yt−n+1)+ wt+1,

with t ϵ (n…….N-H) and h ϵ (1,…….,H) and returns a multi-step forecast by
concatenating the H predictions. Since the Direct strategy does not use any
approximated values to compute the
forecasts. First, since the H models are learned inde-pendently no statistical
dependencies between the predictions is considered. Second direct methods
often require higher functional complex-ity (Tong,1983) than iterated ones in
order to model the stochastic dependency between two series values at two
distant instants ( Guo, 1999). Last but not least, this strategy demands a large
computational time since the number of models to learn is equal to the size of
the horizon.

RESULTS
As was with the RF model and the XGBoost model, the ANN model LSTM utilized the
same data. In the case of artificial neural networks, the approach use stacked hidden
layers, and depending on the Epoch, the data results may vary.

In order to analyze the earlier data, the LSTM model used the Keras deep learning
library from the Python language. Furthermore, the LSTM uses the Keras deep
learning library with a default activation function that outputs a value between 1 and
1 via the hyperbolic tangent function. As such, by using the min max scaler, the input
values are similarly changed to a measure between 1 and 1. The behavior of the LSTM
model can change depending on the optimizer and activation function used.

9