Welcome to KnowledgeMiner Software. We develop apps for the Mac based on original self-organizing modeling and analysis concepts, Insights and Ockham. KnowledgeMiner Insights and Ockham is outstanding parallel 64-bit self-organizing data mining and sensitivity analysis software based on sophisticated deep learning GMDH algorithms. It is designed to extract new knowledge in form of predictive analytical models from noisy data stored in Excel or other data sources, automatically. Implement your predictive models generated with Insights in your research or web projects easily by ready-to-use Python, Objective-C, AppleScript, Matlab, or Excel code.
Welcome to KnowledgeMiner Software. We develop apps for the Mac based on original self-organizing modeling and analysis concepts, Insights and Ockham. KnowledgeMiner Insights and Ockham is outstanding parallel 64-bit self-organizing data mining and sensitivity analysis software based on sophisticated deep learning GMDH algorithms. Insights is designed to extract new knowledge in form of predictive analytical models from noisy data stored in Excel or other data sources, automatically. Obtaining a model from data that reliably reflects the underlying relationship in the data with some certainty is hard work. This is especially true for noisy, disturbed data. Noisy data are everywhere so you most probably will use them. To systematically avoid overfitting - that is, when the model fits to random cases (noise) and therefore can only have poor predictive power, which makes the model useless -, to get optimized transfer functions in Active Neurons, and to self-organize robust optimal complex, noise-immune models with optimal predictive power, Insights employs original concepts of model validation at different levels of the self-organizing modeling process. Together with our Live Prediction Validation in Insights, application of data mining models is now more reliable, stable, and valuable than ever before. Commonly, binary classification tools require that the number of positive and negative cases in a data sample are of nearly equal size, i.e., a prevalence of about 50%, and that the misclassification costs for false positives and false negatives are also equal. The same is true for the benefits of true positives and true negatives. These three assumptions, however, are not fulfilled for most real-world problems. Imagine a medical disease diagnosis problem. It is intuitively clear that the number of persons of a whole population who have the disease is essentially smaller than those who doesn't. Here, prevalence is very small. Also, the costs (personal, medical, societal) of diagnosing a healthy person sick are quite different the costs of diagnosing a sick person healthy - depending on the disease, but also on the purpose of the diagnosis: is it a first screening or a final test, for example. This means, classification accuracy alone isn't what you are interested in. First of all, it is the cost that has to be minimized. Insights provides the capability of building tailored models in an intuitive and simple way: define the costs and prevalence of the problem or let Insights use appropriate values automatically and come up with a dedicated, cost-optimized predictive classification model. Implement your predictive models generated with Insights in your research or web projects easily by ready-to-use Python, Objective-C, AppleScript, Matlab, or Excel spreadsheet code.
Ockham is an easy to use Excel based app which offers the possibility to perform rigorous sensitivity analyses for a high number of parameters. Ockham will undoubtedly be a valuable tool for finance and industry practitioners across a wide spectrum of disciplines including but not limited to: Financial and risk analysts, pharmaceutical scientists, environmental engineers, oil and gas reservoir simulation engineers, and government agencies and local authorities. The most widely used type of sensitivity analysis consists of 'one-factor-at-a-time' approaches, which consist of analyzing the effect of varying one model parameter whilst all others are kept constant. Global sensitivity analysis (GSA) approaches rely on the calculation of importance measures based on the simultaneous variation of input parameters. Unlike local sensitivity analysis methods, the GSA method implemented in Ockham is able to explore the parameter space more thoroughly and consistently, accounting for interactions between these parameters
insights,deep learning,knowledgeminer,knowledge,miner,data mining,predictive modeling,predictive analytics,knowledge discovery,cost,cost-sensitive,cost-optimized,imbalanced data,many inputs,prediction workflow,GMDH,self-organizing,predict,modeling,spreadsheet,excel,causal relationship,noise immunity,adaptive learning,inductive learning hdmr, sensitivity, analysis, global sensitivity, high dimensional model representation, Sobol, index, indices, derivative based global sensitivity measures, analytical, predictive, models, data mining, occam, ockham, occams razor, ockhams razor