Notes on Machine Learning and Data Analysis
The Internet of things is the world of networking devices (portables, vehicles, buildings) embedded with sensors and software. Environment and energy monitoring Medical and health monitoring Consumer support, sales monitoring Urban management and manufacturing...
The Master of Science in Industrial and Applied Mathematics (MSIAM) offers a large spectrum of courses, covering areas where the research in applied math in Grenoble is at the best level. Our graduates are...
Lectures for Institute of Applied Mathematics, Middle East Technical University Problem Statements in Time Series Forecasting Part1: PDF The talk includes statements of the machine learning problems in risk management, as well as consumption...
The main goal is to show how a quantitative model could be recognized among daily routines. The model is a mathematical representation of our knowledge about some investigated phenomenon. See the presentation.
The project contains a lecture course “Data Mining in Business Analytics”, materials of workshops and code. It is devoted to algorithms of data analysis and their applications. It includes practical examples from business and...
Report description, place it in the next line after the title. Below this description the Content section will be generated automatically. Contents The Theory The Practice After the Content section useful comments could be...
What is Singular Value Decomposition? In linear algebra, singular value decomposition (SVD) is a factorization of a real or complex matrix. It is a generalization of the eigendecomposition of a normal square matrix with...
It shows how to use minimal least squares method to fit data. We will generate one-dimensional regression sample set. Tree linear regression models will be constructed, their parameters will be tuned according to the...
This demo shows how to use indices of sorted sets and how to recover the unsorted set from the sorted one. % A set of values is gven; each value has its index k...
Plot the 1st Principal Component of the 2D sample set. The script uses a standard 1PC procedure and do not canter the matrix as it recommnded. Contents Get the data Normalize the matrix Caclulate...
This demo shows how to deal with the different hypothesis on data generation. The data generation hypothesis here is an assumption about the link function. We have a synthetic model and three link functions....
Contents Receiver Operating Characteristic example Construct the sample set Plot the histogram Construct the ROC Plot the ROC curve Receiver Operating Characteristic example ROC analysis provides tools to select possibly optimal models and to...
Below there are several peculiar counters, used in various algorithms on regression modeling Contents Count the features Count 2^n combinations of elements in a set Count 2^n combinations with reinsertion for n=1,2,… Also see...
This demo shows how to compute show a separation hyperplane to classify objects. The hyperplane separates one class of objects from another. Contents Generate model data in 2D The simplest way to get data...
The Newton-Raphson algorithm is used to obtain the optimal parameters of the regression model Contents Create a demonstration data set Set the constant for iteration convergence Define the initial value of the parameters The...
Use one of the following data samples to show the forecast Contents 1) electricity consumption 2) triangle example 3) trapezoid example 4) sine example run the forecasting algorithm show the results file: demo_ssa_forecast 1)...
The target function for optimization in regression analysis usually requires additional parameters and must be placed apart from the main module. It is convenient to have several target functions and use them in turn....
Bank credit scoring: automatic model generation and selection, Seminar on Data Analysis in Business Application at the Moscow State University: Sept 2010 (Rus) [strijov10scoring_slides_ru.pdf, Ru] How to make Integral Indicators using Data and Expert...
Though our online index calculator that performs automatic index construction is suspended now, we briefly describe the project and provide instructions on building indices using our technics.
Introduction There are lots of ways to construct indices. However, when algorithms are chosen and some results obtained, the following question arises: – How to show adequacy of the calculated indices? To answer the...
The Multivariate Regression Composer (MVR) is an open-source software for generating and selecting non-linear regression models in Matlab. The basic version of the MVR Composer could be downloaded as a zipped file (release 61)...
Time series has similar patterns. A pattern consists of several segments. Each segment could be represented as a simple parametric regression function. The whole pattern is the sequence of concatenated regression functions.The following information...
The problem of model generation is illustrated with a linear regression model of a single variable. See the example. Contents Make synthetic data using a model from generated set Assign set of the primitive...
LARS is one of the most effective algorithms to select linear regression models. It is not so greedy as step-wise regression and takes not so much steps as Lasso. Contents Create synthetic data Run...