IMSL Numerical Libraries
Battle-Tested Algorithms From Prototype to Production
Analyzing data has never been more important — or harder. Getting actionable information from your large and disparate datasets can often determine if your organization meets its goals. Create competitive differentiation and unlock innovation by using the most trusted, tested, and reliable algorithms available. Backed by a team of mathematicians and statisticians, IMSL® Numerical Libraries allow you to address complex problems quickly with a variety of readily-available algorithms. With IMSL you get consistency from prototype to production.
The largest collection of commercially-available mathematical and statistical functions for data mining and analysis, IMSL embeddable algorithms are used in a broad range of applications across all industries. Organizations in finance, telecommunications, oil and gas, government, aerospace, and manufacturing depend on the robust and portable IMSL Libraries to efficiently build high-performance, mission-critical applications, including applications used to enable the innovative study of the human genome. Create, innovate, and implement technology to meet your strategic objectives.
Embeddable Mathematical and Statistical Functionality
IMSL Libraries save development time by providing optimized mathematical and statistical algorithms that can be embedded into C, C++, Java, Fortran, and Python applications, including many databases. IMSL enhances application performance, reliability, portability, scalability, and maintainability as well as developer productivity. IMSL Libraries are supported across a wide range of languages as well as hardware and operating system environments including Windows, Linux, and many UNIX platforms.
|Data mining and forecasting functionality||Statistical functionality||Mathematical functionality|
|Stochastic Gradient Boosting||Summary Statistics||Optimization|
|Decision Trees||Time Series and Forecasting||Matrix Operations|
|Regression||Nonparametric Tests||Linear Algebra|
|Vector Auto-Regression/Vector Error Correction Model||Analysis of Variance||Eigensystem Analysis|
|Apriori Analysis||Generalized Linear Models||Interpolation and Approximation|
|Cluster Analysis||Goodness of Fit||Quadrature|
|Kohonen Self Organizing Maps||Distribution Functions||Differential Equations|
|Neural Networks||Random Number Generation||PDEs|
|Auto_ARIMA||Hypothesis Testing||Feynman-Kac Solver|
|ARCH, GARCH||Design of Experiments||Transforms|
|Support Vector Machines||Visualization||Nonlinear Equations|
|Genetic Algorithms||Statistical Process Control||Linear and Nonlinear Programming
including Sparse LP Solver
|NaÃ¯ve Bayes||Multivariate Analysis||Special Functions|
|Logistic Regression||Correlations and Covariance||Utilities|
|Principal Components Analysis|
|Bayesian Seasonal Model|