Neural networks In business
Definition of Neural network
The simplest definition of a neural network, more properly referred to as an ‘artificial’ neural network (ANN), is provided by the inventor of one of the first neuro computers, Dr. Robert Hecht-Nielsen. He defines a neural network as:“…a computing system made up of a number of simple, highly interconnected processing elements, which process information by their dynamic state response to external inputs.”
Although the mathematics involved with neural networking is not a trivial matter, a user can rather easily gain at least an operational understanding of their structure and function.
Historical background
Neural network simulations appear to be a recent development. However, this field was established before the advent of computers, and has survived at least one major setback and several eras.
The first artificial neuron was produced in 1943 by the neurophysiologist Warren McCulloch and the logician Walter Pits. But the technology available at that time did not allow them to do too much. Hebb (1949) developed the first learning rule (on the premise that if two neurons were active at the same time the strength between them should be increased) .
During the 50’s and 60’s many researchers worked on the perceptions amidst great excitement.1969 saw the death of neural network research for about 15 years Minsky & Papert. Only in the mid 80’s (Parker and LeCun) was interest revived (in fact Werbos discovered algorithm in 1974) Many of the principles can still be seen in neural networks of today.
Advantages of neural networks
A trained neural network can be thought of as an “expert” in the category of information it has been given to analyses. This expert can then be used to provide projections given new situations of interest and answer “what if” questions. Other advantages include:
1. Adaptive learning: An ability to learn how to do tasks based on the data given for training or initial experience.
2. Self-Organization: An ANN can create its own organization or representation of the information it receives during learning time.
3. Real Time Operation: ANN computations may be carried out in parallel, and special hardware devices are being designed and manufactured which take advantage of this capability.
Fault Tolerance via Redundant Information Coding: Partial destruction of a network leads to the corresponding degradation of performance. However, some network capabilities may be retained even with major network damage.
Applications of neural networks
Neural networks have broad applicability to real world business problems. In fact, they have already been successfully applied in many industries. Since neural networks are best at identifying patterns or trends in data, they are well suited for prediction or forecasting needs including:
- sales forecasting
- industrial process control
- customer research
- data validation
- risk management
- target marketing
But to give some more specific examples; ANN are also used in the following specific paradigms: recognition of speakers in communications; diagnosis of hepatitis; recovery of telecommunications from faulty software; interpretation of multi meaning Chinese words; undersea mine detection; texture analysis; three-dimensional object recognition; hand-written word recognition; and facial recognition.
Neural Networks in Business
Business is a diverted field with several general areas of specialization such as accounting or financial analysis. Almost any neural network application would fit into one business area or financial analysis.
There is some potential for using neural networks for business purposes, including resource allocation and scheduling. There is also a strong potential for using neural networks for database mining that is, searching for patterns implicit within the explicitly stored information in databases.
Most industrial processes are well equipped with on-line process sensors, and in some cases analytical sensors. These sensors allow the process computer to acquire on-line process information and make appropriate control to maintain consistent product quality. Most of the control strategies are feedback control. However, since these variables are of crucial importance, lab tests of the product samples are usually conducted to measure the product quality off-line on a specified interval base. In the situation where lab tests are conducted, a time-delay of one to ten hours is often incurred.
Since the functional relationship between the quality variables and other variables are usually nonlinear, the neural network approach is a convenient choice for modeling the relationship. The neural network approach to building intelligent sensors is fundamentally an empirical approach based on process data —
· short term debt;
· day average escort;
· credits vs customers;
· credits vs suppliers;
· equity/total debts;
· debts vs banks + ics/financial debts;
· financial burden./EBIDTA;
· self-financing/intangible assets;
· Equity/assets.
· All inputs were normalized between the values from –1 to +1.
This step serves to ensure that data are processed, so that they are more easily readable by the network. The data are included in a given range; in our case the interval is equal to [–1, 1]1 . The variable used as output is only one, and it is the score. The purpose of the network is to minimize the difference between the desired response and the one provided by the network. The aim of this network is to correctly classify the companies of our sample, to create classes more homogeneous internally and more heterogeneous among themselves.
Conclusion
The computing world has a lot to gain from neural networks. Their ability to learn by example makes them very flexible and powerful. Furthermore there is no need to devise an algorithm in order to perform a specific task. Neural networks also contribute to other areas of research such as neurology and psychology.
Finally, I would like to state that even though neural networks have a huge potential we will only get the best of them when they are integrated with computing.
