Description
Describes what is neural network and its application of neural networks in cash forecasting.
Neural Networks
GROUP - 4
INTRODUCTION
“BUY” and “SELL” recommendations “SHORT TERM VIEW”, “LONG TERM VIEW” – How exactly do experts arrive at these conclusions ?
• •charts,
pet indicators, and intuition generally used to navigate through the massive amounts of financial information available.
•
Herculean task to predict the future economy or stock market in general with the great number of influences involved. There is even new scientific evidence that massive systems such as the U.S. economy or the weather are not predictable very far into the future (due to the effects of chaos).
•To
assist people in making forecasts for particular markets, there are more than 250 computer programs available.
•Traditionally,
these systems are expensive, require complex programming, use surveys of financial experts to define the "game rules", and are still limited in their ability to think like people.
NEW AGE THINKERS – NEURAL NETWORKS
•Neural
network programs are a new kind of computing tool which simulate the structure and operation of the human brain. They mimic many of the brain's most powerful abilities, including pattern recognition, association, and the ability to generalize by observing examples.
•Neural
Networks can be given subjective information as well as statistics and are not limited to any particular financial theory.
•Using
a neural network for advice means you don't have to decipher complex wave forms to find a trend. The network will determine which influences correlate to each other, if there are patterns, filtering out the noise, and picking up overall trends.
•You
can retrain a network to use new, updated information in minutes.
CONTD …..
To summarize neural networks –
•
can learn from experience instead of following equations or rules.
•can
be asked to consider hundreds of different influences, more than most people can digest.
•
won't be overwhelmed by decades of statistics.
•can
be used in place of, or in addition to, traditional methods.
THINKING PROCESS OF NEURAL NETWORKS
•
A close analogy with the human brain.
•The
brain is composed of hundreds of billions of nerve cells (neurons) which are massively connected to each other. Recently biologists have learned that it is the way the cells are connected which provides us with intelligence, rather than what is in the cells.
•Neural
networks simulate the structure and operation of the brain's neurons and connections.
•A new
neural network starts out with a "blank mind". The network is taught about a specific problem, such as predicting a stock's price, using a technique called training.
•A new
neural network is shown some data and it guesses what the result should be. At first the guesses are gibberish. When the network is wrong, it is corrected.
CONTD…..
•
The network is shown lots of data, over and over until is learns all the data and results. Like a person, a trained neural network can generalize, making a reasonable guess when given data which is different than any it has seen before.
•You
decide what information to provide and the network finds the patterns, trends, and hidden relationships.
INSIDE A NEURAL NETWORK
•Network
consists of many neurons, grouped into layers.
•INPUT
LAYER LAYER LAYER
•HIDDEN •OUTPUT
•The
connections, which can be thought of as lines between the layers, are what get corrected during training.
•The
effectiveness of functioning lies in strengthening some connections and weakening others, so that the next time example data is presented the neural network will output a more correct answer.
An Example of training
? ?
Pattern recognition (Light and dark) All dendrites either in excitory or inhibitory mode.
LEARNING through CORRECTION
•The
connections allow the neurons to communicate with each other and form answers.
•When
the network makes a wrong guess, an adjustment is made to the way neurons are connected, thus it is able to learn.
•With
most commercially available neural network programs (the network is created and trained by the program itself; all you have to do is provide the data and the expected results for training.
DESIGNING a NEURAL NETWORK
•
The first thing is to decide what result you want the network to provide for you and what information it will use to arrive at the result.
•It's
best to give the network lots of information. If you are unsure if there is a relationship, provide the data (for example between how the good the weather is over the U.S. and the DOW). The neural network will figure out if the information is important and will learn to ignore anything irrelevant.
•Sometimes
a possibly irrelevant piece of information can allow the network to make distinctions which we are not aware of. If there's no correlation, the network will just ignore the information. Mathematical models aren't this flexible.
•A neural
network need not follow any particular economic theory, it can easily adopt a generalist view taking inputs from “technical analysis”, “fundamental analysis” and “monetarist” school of thoughts.
AN EXAMPLE
•
We want to make a network which will predict the price of the Dow Jones Industrial Average (DOW) on a month to month average basis, one month in advance.
•The
information to provide the network might include the Consumer Price Index (CPI), the price of crude oil, the inflation rate, the prime interest rate, the Gross National Product (GNP), and other indicators.
•A better
design of data would include a better input in terms of period and
variety.
CONTD……
Mon
CPI
CPI-1
CPI-3
Oil
Oil-1
Oil-3
Dow
Dow-1
Dow-3
Dow Ave (output)
JAN
229
220
146
20
21.5
19.5
2645
2652
2597
2647
FEB
235
226
155
19.8
20
19.3
2633
2645
2585
2637
MAR
244
235
164
19.6
19.8
18.1
2627
2633
2579
2630
APR
261
244
186
19.6
19.6
18.1
2611
2627
2563
2620
MAY
276
261
196
19.5
19.6
18
2630
2611
2582
2638
JUN
281
276
207
19.5
19.5
18
2637
2630
2589
2635
JUL
296
287
212
19.3
19.5
17.8
2640
2637
2592
2641
EFFECTIVENESS
•A neural
network is most expert when it is trained for a particular task, such as the future price of a certain stock or a group of related stocks
•It
is very difficult to train a network to predict for many diverse kinds of stocks, since the stocks will react differently to various influences. It would be a massive network that may have trouble learning so many different relationships.
OTHER USES….
BOND RATING PREDICTIONS –
•Trained
network forecasts next year's Standard & Poor's and Moody's corporate bond ratings (both are industry standards) from the previous year's S & P and Moody's ratings and 23 other measures of each company's financial strength, such as
•income, •sales, •
returns on equity, growth in sales,
•5-year •debt
load.
Each of these factors is assigned to its own input neuron, and each company's ratings for next year are the outputs of the network.
CONTD……
MUTUAL FUND PREDICTIONS – Network relies on historically-available numerical data of the kind typically found in back-issues of the Wall Street Journal. These indicators include such factors as
•the • •
DOW Industrial,
DOW Utilities DOW Transportation & Poor's 500 weekly averages.
•Standard
Several years worth of data was gathered for the four initial conditions (the inputs) and the ten results (the outputs). Closing weekly averages on Friday are collected and the new data Is used to predict prices of the 10 mutual funds for the next week.
Application of neural networks in cash forecasting
Existing approaches to cash forecasting Time-series method ? Factor analysis method ? Expert systems approach
?
Neural Networks approach
?
The network maps the relationships between various factors affecting the cash withdrawal and the actual cash withdrawal. The forecast error for each pair of actual and forecasted cash withdrawal can be given by
?
STEP 1 – DATA COLLECTION
Source: State Bank of India, Chandigarh.
Step 2 - ARCHITECTURE
Following parameters are of utmost importance while imparting the design – ? Selecting the number of layers. ? Basic decision about the number of neurons to be used in each layer ? Choosing the appropriate neuron transfer functions.
Step 3 – Determining the layer size
Input layer size –
?
? ?
?
?
Mainly calendar effects are included as parameters affecting cash withdrawal in this model, Working Day Week Day Holiday Salary day
Number of neurons needed in the input layer – 4 Number of neurons needed in the output layer – 1 (forecasted cash values)
Optimal hidden layer size
?
?
Usual method – Trial and error, practically forward selection or backward selection used for the estimation purpose – Forward selection - Starts with choosing an appropriate criterion for evaluating the performance of the network. Then we select a small number of hidden neurons; record its performance i.e forecast accuracy. Next we slightly increase the hidden neurons, train and test until the error is acceptably small or no significant improvement is noted. Backward selection - Starts with a large number of hidden neurons and the decreases the number gradually.
?
Contd….
?
Optimal number of neurons in hidden layer (using forward selection – 9)
Step 4 – Deciding upon the transfer function
Contd….
?
Best transfer function – tansig-logsig
TheResults
THANK YOU
doc_390643569.ppt
Describes what is neural network and its application of neural networks in cash forecasting.
Neural Networks
GROUP - 4
INTRODUCTION
“BUY” and “SELL” recommendations “SHORT TERM VIEW”, “LONG TERM VIEW” – How exactly do experts arrive at these conclusions ?
• •charts,
pet indicators, and intuition generally used to navigate through the massive amounts of financial information available.
•
Herculean task to predict the future economy or stock market in general with the great number of influences involved. There is even new scientific evidence that massive systems such as the U.S. economy or the weather are not predictable very far into the future (due to the effects of chaos).
•To
assist people in making forecasts for particular markets, there are more than 250 computer programs available.
•Traditionally,
these systems are expensive, require complex programming, use surveys of financial experts to define the "game rules", and are still limited in their ability to think like people.
NEW AGE THINKERS – NEURAL NETWORKS
•Neural
network programs are a new kind of computing tool which simulate the structure and operation of the human brain. They mimic many of the brain's most powerful abilities, including pattern recognition, association, and the ability to generalize by observing examples.
•Neural
Networks can be given subjective information as well as statistics and are not limited to any particular financial theory.
•Using
a neural network for advice means you don't have to decipher complex wave forms to find a trend. The network will determine which influences correlate to each other, if there are patterns, filtering out the noise, and picking up overall trends.
•You
can retrain a network to use new, updated information in minutes.
CONTD …..
To summarize neural networks –
•
can learn from experience instead of following equations or rules.
•can
be asked to consider hundreds of different influences, more than most people can digest.
•
won't be overwhelmed by decades of statistics.
•can
be used in place of, or in addition to, traditional methods.
THINKING PROCESS OF NEURAL NETWORKS
•
A close analogy with the human brain.
•The
brain is composed of hundreds of billions of nerve cells (neurons) which are massively connected to each other. Recently biologists have learned that it is the way the cells are connected which provides us with intelligence, rather than what is in the cells.
•Neural
networks simulate the structure and operation of the brain's neurons and connections.
•A new
neural network starts out with a "blank mind". The network is taught about a specific problem, such as predicting a stock's price, using a technique called training.
•A new
neural network is shown some data and it guesses what the result should be. At first the guesses are gibberish. When the network is wrong, it is corrected.
CONTD…..
•
The network is shown lots of data, over and over until is learns all the data and results. Like a person, a trained neural network can generalize, making a reasonable guess when given data which is different than any it has seen before.
•You
decide what information to provide and the network finds the patterns, trends, and hidden relationships.
INSIDE A NEURAL NETWORK
•Network
consists of many neurons, grouped into layers.
•INPUT
LAYER LAYER LAYER
•HIDDEN •OUTPUT
•The
connections, which can be thought of as lines between the layers, are what get corrected during training.
•The
effectiveness of functioning lies in strengthening some connections and weakening others, so that the next time example data is presented the neural network will output a more correct answer.
An Example of training
? ?
Pattern recognition (Light and dark) All dendrites either in excitory or inhibitory mode.
LEARNING through CORRECTION
•The
connections allow the neurons to communicate with each other and form answers.
•When
the network makes a wrong guess, an adjustment is made to the way neurons are connected, thus it is able to learn.
•With
most commercially available neural network programs (the network is created and trained by the program itself; all you have to do is provide the data and the expected results for training.
DESIGNING a NEURAL NETWORK
•
The first thing is to decide what result you want the network to provide for you and what information it will use to arrive at the result.
•It's
best to give the network lots of information. If you are unsure if there is a relationship, provide the data (for example between how the good the weather is over the U.S. and the DOW). The neural network will figure out if the information is important and will learn to ignore anything irrelevant.
•Sometimes
a possibly irrelevant piece of information can allow the network to make distinctions which we are not aware of. If there's no correlation, the network will just ignore the information. Mathematical models aren't this flexible.
•A neural
network need not follow any particular economic theory, it can easily adopt a generalist view taking inputs from “technical analysis”, “fundamental analysis” and “monetarist” school of thoughts.
AN EXAMPLE
•
We want to make a network which will predict the price of the Dow Jones Industrial Average (DOW) on a month to month average basis, one month in advance.
•The
information to provide the network might include the Consumer Price Index (CPI), the price of crude oil, the inflation rate, the prime interest rate, the Gross National Product (GNP), and other indicators.
•A better
design of data would include a better input in terms of period and
variety.
CONTD……
Mon
CPI
CPI-1
CPI-3
Oil
Oil-1
Oil-3
Dow
Dow-1
Dow-3
Dow Ave (output)
JAN
229
220
146
20
21.5
19.5
2645
2652
2597
2647
FEB
235
226
155
19.8
20
19.3
2633
2645
2585
2637
MAR
244
235
164
19.6
19.8
18.1
2627
2633
2579
2630
APR
261
244
186
19.6
19.6
18.1
2611
2627
2563
2620
MAY
276
261
196
19.5
19.6
18
2630
2611
2582
2638
JUN
281
276
207
19.5
19.5
18
2637
2630
2589
2635
JUL
296
287
212
19.3
19.5
17.8
2640
2637
2592
2641
EFFECTIVENESS
•A neural
network is most expert when it is trained for a particular task, such as the future price of a certain stock or a group of related stocks
•It
is very difficult to train a network to predict for many diverse kinds of stocks, since the stocks will react differently to various influences. It would be a massive network that may have trouble learning so many different relationships.
OTHER USES….
BOND RATING PREDICTIONS –
•Trained
network forecasts next year's Standard & Poor's and Moody's corporate bond ratings (both are industry standards) from the previous year's S & P and Moody's ratings and 23 other measures of each company's financial strength, such as
•income, •sales, •
returns on equity, growth in sales,
•5-year •debt
load.
Each of these factors is assigned to its own input neuron, and each company's ratings for next year are the outputs of the network.
CONTD……
MUTUAL FUND PREDICTIONS – Network relies on historically-available numerical data of the kind typically found in back-issues of the Wall Street Journal. These indicators include such factors as
•the • •
DOW Industrial,
DOW Utilities DOW Transportation & Poor's 500 weekly averages.
•Standard
Several years worth of data was gathered for the four initial conditions (the inputs) and the ten results (the outputs). Closing weekly averages on Friday are collected and the new data Is used to predict prices of the 10 mutual funds for the next week.
Application of neural networks in cash forecasting
Existing approaches to cash forecasting Time-series method ? Factor analysis method ? Expert systems approach
?
Neural Networks approach
?
The network maps the relationships between various factors affecting the cash withdrawal and the actual cash withdrawal. The forecast error for each pair of actual and forecasted cash withdrawal can be given by
?
STEP 1 – DATA COLLECTION
Source: State Bank of India, Chandigarh.
Step 2 - ARCHITECTURE
Following parameters are of utmost importance while imparting the design – ? Selecting the number of layers. ? Basic decision about the number of neurons to be used in each layer ? Choosing the appropriate neuron transfer functions.
Step 3 – Determining the layer size
Input layer size –
?
? ?
?
?
Mainly calendar effects are included as parameters affecting cash withdrawal in this model, Working Day Week Day Holiday Salary day
Number of neurons needed in the input layer – 4 Number of neurons needed in the output layer – 1 (forecasted cash values)
Optimal hidden layer size
?
?
Usual method – Trial and error, practically forward selection or backward selection used for the estimation purpose – Forward selection - Starts with choosing an appropriate criterion for evaluating the performance of the network. Then we select a small number of hidden neurons; record its performance i.e forecast accuracy. Next we slightly increase the hidden neurons, train and test until the error is acceptably small or no significant improvement is noted. Backward selection - Starts with a large number of hidden neurons and the decreases the number gradually.
?
Contd….
?
Optimal number of neurons in hidden layer (using forward selection – 9)
Step 4 – Deciding upon the transfer function
Contd….
?
Best transfer function – tansig-logsig
TheResults
THANK YOU
doc_390643569.ppt