Decision AI

Decision AI, Artificial Intelligence (AI) software toolkitDecision AI is an Artificial Intelligence (AI) software toolkit for Business Process Improvement and Decision Making but may also be used for many other purposes (see below). DecisionAI is the MS Windows version of the DecisionAI Google Sheets Add-on. DecisionAI runs on all versions of Microsoft Windows.

Decision AI supports both mixed AI and numerical AI models. In mixed AI models the input data may be both textual and numerical and the AI is using a special Decision Tree based model. In the numerical AI model all data must be integer or decimal numbers and the AI is using a support vectors based algorithm (SVM).

DecisionAI also contains extensive data analysis tools (statistical analysis, control charts, etc.) for your Business Process Improvement (or six-sigma) projects. These tools can also be used stand alone.
DecisionAI can be used (after training the AI) to quickly make decisions about many different often complex matters as e.g.:
  • which next process step the employee (or client, product, etc.) has to take,
  • decide if an action should be taken or not,
  • select an employee (or client, product, etc.) for a specific task (or action, marketing campaign, etc.),
  • root cause analyses,
  • etc.
 AI-TOOLKIT Download

AI-TOOLKIT Helpdesk

 Software Feedback Form

DecisionAI can also be used for non business process improvement decisions as for example whether to buy a stock on the stock exchange (with well defined AI training parameters), to quickly classify specific species or plants depending on some characteristics, knowledge management, to quickly recognize specific illnesses depending on several symptoms in healthcare, classify sounds or images (by first transferring them to numerical data), … etc.

DecisionAI is very easy to use, it hides the complex algorithm of AI machine learning and with just a few input parameters you can make great improvements to your decision making process and accuracy. People make often mistakes because of complex issues depending on many parameters. A well trained AI will not make a mistake because of complexity but only if it is not trained well enough by you!

The built-in MS Excel import module automatically converts different types of data files (numerical, text) to the DecisionAI format.

DecisionAI Server Included!

The DecisionAI Server can be used to automatically process input data files for prediction e.g. from an other software package. You can choose the time frequency with which the server will check for new input after it is started. The other software package can then read in the results after they appear in the 'server/out' directory. In this way you can also stream new data  (any amount = big data ready) to DecisionAI for  processing.

 AI-TOOLKIT Training Video's, Decision AI Professional, DeepAI, VisionAI

Artificial Intelligence (AI) software toolkit for Business Process Improvement and Decision Making

The Mixed AI Model

By feeding the appropriate data (textual and/or numerical) to the Decision AI Mixed AI model, together with the right decisions, you can train the AI and use it later to help you make the right decision fast. Very complex issues can be decided in this way very quickly with great confidence. The accuracy of the decisions will depend on how good you train the AI.

You can also define an optional data header row with the 'cost' of each parameter (feature). The cost can be e.g. the time needed to perform the 'feature process' the parameter belongs to, the cost of making the measurement to get the parameter data (e.g. because of the used equipment), the cost of equipment, the cost of the man hours of a specialist, etc. The unit is not important, it can be any time unit, or any length unit, or any kind of money unit, .... BUT all of the parameters (features) need to have the same unit and need all be defined or all not defined! When defined the algorithm will take the cost of each feature into account and will optimize the AI model for the cheapest solution.

Example AI training data to decide whether to play golf or not depending on weather conditions:

AI Training data

By changing some advanced parameters in the Settings you can influence the AI model building algorithm. These parameters are the different types of splitting criteria, whether to use the gain ratio, pruning level and variance correction.

If you checked the 'Show Decision Tree' option in the settings a new screen will appear in the sidebar with a tree representation of the model. The AI builds this decision tree model as a kind of thinking map in order to be able to quickly find the appropriate decision by traversing this tree depending on the input parameters.

AI Decision Tree

After the model is built you can save it for later use.

You can use your trained AI to make quickly and accurately a decision depending on several input parameters. The accuracy of the decision made by the AI will depend on how good you have trained the AI.

There is also an automatic AI request form generator which can be used to ask a question from the AI with the necessary parameters presented.

automatic AI request form generator

The Numerical AI Model

The numerical AI Model works similarly to the Mixed AI model but it only accepts numbers as input data and it can model Classification and also Regression. The AI is using a so called support vectors machine based algorithm (SVM). The numerical AI Model can handle more complex input data than the Mixed AI model.

There are more input parameters in the settings for this type of model than for the Mixed AI model and the values of some of the parameters are crucial! For this reason there is a built in parameter optimization module.

You can also request the probability of each prediction.

Data Analysis Toolkit

With the data analysis toolkit you can analyze your data automatically. After opening the data file you will be presented with all important statistics, data and distribution charts. You can select which column of the data to analyze or decide whether the data is sub-grouped. You can also generate automatically a control chart where all possible problems will be indicated with your data (statistical process control).

DecisionAIPro Data Analysis Toolkit, Control Chart, Statistics, Distribution

The Automatic Classification Toolkit

From version 2.2.1.1 DecisionAI includes an automatic data classification toolkit which can be used to classify unclassified numerical data. After classifying the data you can use the data to train an AI model.

In case you have numerical data which is not classified yet (there is no decision variable) then you can use the Auto Classification Toolkit to automatically classify the data. Please note that it is always better to classify the data yourself but this may not always be possible e.g. in case you have a lot of data or when the data is not easily classifiable.

You can start the Auto Classification Toolkit in the Data menu or with the 'Auto Classification' toolbar button. The toolkit is very easy to use. First you need to open the data and then set the number of required classes (decisions) in the settings pane on the right side of the screen. The other default options will provide good results in the most of the cases but you can still adjust some advanced parameters in the settings also. For most of the parameters there is a built-in mouse over tooltip help.
If you are satisfied with the input parameters then just push the 'Classify' button or menu and the classification results will be filled in the first column of the data sheet. Each class is designated with an integer number starting from 0!

Please note that the 'Data Transformation Options' transform the data before starting the classification. This can provide in some specific cases better classification results.

You can export the data in MS Excel format by clicking on the Export Data toolbar button or by selecting the 'Export Data' command in the File menu.

After exporting the data in MS Excel format you can easily modify and save the data as an SSV file which is needed for training a numerical AI model.




 AI-TOOLKIT Download


 AI-TOOLKIT Training Video's, Decision AI Professional, DeepAI, VisionAI


Decision AI and the Decision AI Artificial Intelligence Engine is (C) Copyright 2016-2018 Zoltan Somogyi, All Rights Reserved 

AI-TOOLKIT Helpdesk


Contact

Contact Person

Address

Antwerp, Belgium

You may use LinkedIn (phone number and email available) or the contact form to the right.

Helpdesk

You may contact the AI-TOOLKIT helpdesk:


Search This Website