User:Analytics447/DRAFTSAS(Software)

A work-in-progress of a SAS (software) Wiki that is more complete, accurate, heavily verified and neutral in tone. Prior negative opinions were not removed, but better balanced and verified. If you feel any of these changes introduce bias or are not an improvement to the Wiki, or have other suggestions, please visit my Talk page using Assume Good Faith. Analytics447 (talk)

SAS is an analytics software suite of over 200 products developed by SAS Institute. SAS draws from statistics, predictive analytics, data mining, data visualization, operations research, graph theory, quality improvement and text analytics to help organizations predict, measure, analyze and decide based on data. Use case scenarios span dozens of industries and applications, including fighting fraud, risk management,  compliance, performance management, customer/marketing analysis and supply chain management.

A SAS application may combine data integration, data quality, data mastering, enterprise data access and data governance to source, cleanse and pool operationally generated and third-party data into an accurate source of input for analytical modeling. Analysis engines then apply a series of transformations, models and testing routines relevant to the use case. Analysis results are delivered to operational systems, dashboards, reports and other graphical user interfaces where they are consolidated, presented and used for automated or business-level decisions.

SAS utilizes grid, in-database, and in-memory computing algorithms and methods to address extremely large data volumes.

SAS Software's Beginnings in Academics
SAS was conceived by Anthony J. Barr in 1966. As a North Carolina State University graduate student from 1962 to 1964, Barr created an analysis of variance (ANOVA) modeling language inspired by statistician Maurice Kendall and a multiple regression program that generated machine code for performing algebraic transformations of raw data. Drawing on those programs and his experience with structured data files, Barr created Statistical Analysis Software (SAS), which was the beginning of the SAS product set. From 1966 to 1968, Barr developed the fundamental structure and language of SAS. In January 1968, Barr and James Goodnight integrated new multiple regression and analysis of variance routines developed by Goodnight into Barr's framework.

In 1973, John Sall joined the project, making extensive programming contributions in econometrics, time series, and matrix algebra. Other participants in the early years included Caroll G. Perkins, Jolayne W. Service, and Jane T. Helwig. Service and Helwig created the early documentation. In 1976, SAS Institute, Inc. was incorporated by Barr, Goodnight, Sall, and Helwig.

The First SAS Products
SAS 71 was released in 1971 as the very first limited release of SAS. SAS 72, released the following year, was more well-rounded and added features for handling missing data and combining data sets.

In 1976, SAS was rebuilt from scratch in SAS 76 with an open architecture that allowed compilers and procedures. It also was able to use any data format on an IBM mainframe, generate reports and handle general linear models. At the time SAS was used by just 100 customers and a single SAS program consisted of 150 boxes of paper cards.

In 1979, SAS/Graph and SAS/ETS products added graphing, econometric and time-series analysis capabilities and were some of the first products added to Base SAS.

The 1980s represented a significant shift from mainframe computers to more widespread accessibility on common desktops. SAS Version 5 in 1983 was the first SAS release for the minicomputer. In 1986, SAS was re-written in C for SAS Version 6. This led to support for UNIX, MS-DOS and Windows the following year through the Multivendor Architecture that SAS is still known for today.

A Maturing Technology
From 1987 to 1999, SAS released a large number of products that supplemented Base SAS for different use cases and added features.

1987 – 1990: SAS introduced SAS/QC, SAS/IML, SAS/STAT, SAS/ASSIST and SAS/CPE. SAS/SHARE introduced concurrent updates to SAS data sets. MultiVendor Architectures was a landmark improvement that allows BASE SAS to run on every major operating system and access any common data source. JMP also shipped for the first time in 1989. 

1991 - 1995: SAS introduced SAS/INSIGHT for data visualization, SAS/CALC, SAS/TOOLKIT, SAS/PH-Clinical, SAS/LAB, ODBC, SAS/SPECTRAVIEW, SAS/SHARE .NET products and a data step debugger as well as Web enablement of SAS software. JMP 2 and 3 were released as well. 

1996 - 1999: SAS introduced SAS/Warehouse Administrator, SAS/IntrNet, Balanced Scorecard, SAS/Enterprise Reporter, SAS HR Vision, as well as CRM products, Risk Dimensions software and an ERP interface for SAS/ACCESS. SAS Version 7 debuted with a new Output Delivery System and improved text editor. In 1999, SAS Version 8 was released. SAS Enterprise Miner, which allowed users to quickly extract information or insights from large data sets, was first introduced the same year. 

Modern Era
Additional releases of JMP were developed in 2000, 2002, 2005, 2007 and 2008. In 2004 SAS released Version 9.0, which was dubbed “Project Mercury” and designed to make SAS accessible by a broader range of business users. Version 9.0 includes custom user interfaces based on the user’s role and the ability to deal with larger data volumes. With version 9, the SAS Enterprise Guide played a more prominent role as the user interface of SAS. SAS Enterprise guide is a point-and-click interface with wizards that allow researchers or analysts to drag and drop data sets, actions and analyses. The U.S. Food and Drug Administration also selected SAS technology as the standard for new drug applications in 2002.

SAS Interaction Management was introduced in 2004 as an enhancement to CRM capabilities. In 2008 SAS announced Project Unity, a project to integrate data quality, data integration and master data management.

Latest Updates
In 2010, SAS Social Media Analytics was released, a tool for social media monitoring, engagement and sentiment analysis. That same year, SAS Rapid Predictive Modeler (RPM) was released to allow less sophisticated users to create basic analytical models in Microsoft Excel. The release of JMP 9 in 2010 added a Microsoft Excel add-in, mapping features, integration with R and improvements to the creation and distribution of custom JMP applications. SAS also made a series of announcements related to High Performance Computing (HPC) technology using grid computing, in-database processing and in-memory technology. The company released an appliance-enabled HPC product using hardware from partners Teradata and EMC Greenplum. In 2011 the company released SAS Forecast Server 4.1 and Enterprise Miner 7.1. Enterprise Miner 7.1 had improved timing elements (survival and time series data mining), insurance pricing models for rate making, credit scorecard extensions and full SAS data mining in Teradata 13.

Customer Intelligence
Many SAS products are used to plan, optimize and execute marketing strategy and customer interaction through workflow, reporting and analytics. SAS often predicts customer interest based on customer data. It develops propensity scores and other measures that are used within marketing campaigns to segment, target and determine content relevance in phone, Web and e-mail communications with customers and prospects. Predictive analytics are also used to prioritize marketing efforts given time, resource and other constraints. SAS products may also resolve customer feedback, prior sales performance and other data to predict, analyze, and optimize the success of a product. Other products collect internal, mobile, Web and social data to create customer profiles. Strategy and planning tools create models and reports that match marketing plans to corporate priorities and resource constraints. Workflow and automation tools support the management of marketing campaigns and customer interactions across channels.

Fraud and Financial Crimes
SAS analyzes financial transaction data as the transactions take place to identify suspicious activity and support related processes. SAS-powered anti-fraud systems can block transactions before they’re processed to prevent losses from suspected fraud. They assist fraud investigators by mapping out the growth of suspected organized fraud networks, and evaluating the likelihood of fraud through a case management system. Some applications use advanced analytics and account data, while others like the Case Management product are focused on process activity.

Governance, Risk and Compliance (GRC)
SAS Enterprise GRC software is used for auditing, compliance, policy and risk and are often combined with other products for finances, supply chain, visualization, activity management or others. The software analyzes events like a financial loss on the stock market or a suspected misrepresentation of financial information. These events trigger an issue and associated action plans, documents, requirements and compliance needs are identified. Then the user is guided through remediation of the issue in order to keep promises, properly audit, maintain compliance or mitigate risk.

IT Resource Management
SAS IT management applications analyze IT resource utilization and performance data about IT assets like servers, storage devices, networks and applications. The application generates reports, analysis, and metrics on IT resource availability and forecasted demand so organizations can plan IT infrastructure resources. It can also examine performance in relation to costs.

Performance Management
SAS’ Performance Management products are intended for executive management and the office of finance to set strategy, align and measure execution, allocate resources and understand profitability. It consists of products specifically for financial management (consolidation, BP&F), cost and profitability analysis (activity-based costing), workforce planning, and corporate strategy (strategy maps and scorecards). Analytic, forecasting and reporting functionalities are built into each of the applications.

Risk Management
SAS risk management applications support the management of economic and regulatory risk related to investments, credit, liability and corporate operations. These applications incorporate data integration, analytics and reporting to understand and assess the risks associated with specific choices and the likelihood of potential outcomes. For example, there are SAS applications specifically for evaluating the likelihood of credit losses, the chances an insurance quote applicant will have future claims or calculating the regulatory capital requirements to meet Pillar 1 of the Basel 2 regulations.

Supply Chain Intelligence
SAS combines transactional, operational and other data to create analysis and reporting to improve supply chain operations. For example, it may make recommendations on inventory levels, optimize delivery routes or uncover warranty claims that are likely to be fraudulent. There are also SAS products specifically for manufacturing in quality and asset maintenance. In many instances, they are used to consolidate data sources covering delivery, inventory, procurement, warranty claims and others.

High Performance Computing
High performance computing (HPC) uses grid computing, in-database analytics and in-memory analytics to solve analytical problems that involve massive computational needs or “big data.” HPC is used to run analytics at a frequency or speed not otherwise available, often to replace processing done every few hours or days with processing every day or within minutes or seconds. For example, the technology can be used to run a logistic regression of bank loan defaults across billions of records in less than 80 seconds, instead of 20 hours. HPC is also used to run analytics against an entire data set, instead of using subset of data. HPC applications can range from fraud detection, credit risk management, revenue optimization, dynamic pricing, telematics, clinical trials and simulation, predictive asset failure, energy big optimization, etc.

Technical Description
A SAS application can have four major parts: The DATA step Graphical User Interfaces (GUI) Procedures Macros</li> </ol>

The Data Step
The DATA step is used to read data into SAS and to prepare the data for analytics and reporting. SAS library engines and remote library services allow access to data stored in external data structures and on remote computer platforms. It uses SAS statements to automate the opening of files, reading and writing records and closing files. This allows the user/programmer to concentrate on the details of working with the data within each record.

Graphical User Interfaces (GUI)
Non-programmer GUIs, like SAS Enterprise Guide, act as a front-end that automates or facilitates the generation of SAS programs. The front-end typically hides functional codes, databases and other components and builds communication between users, software or hardware. GUIs access SAS components using SAS statements, functions and procedures written in an application programming interface (API).

Procedures
Procedures provide specific functionality, such as performing data management, statistical analysis, writing reports, or printing. SAS has an extensive SQL procedure for SQL programmers to use SAS with little additional knowledge.

Macros
There are macro programming extensions that allow for rationalization of repetitive sections of the program. SAS macros are a catalog entry that contains a group of compiled program statements and stored text. Proper imperative and procedural programming constructs can be simulated by use of the "open code" macros or the Interactive Matrix Language SAS/IML component. Macro code in a SAS program, if any, undergoes preprocessing. At run time, DATA steps are compiled and procedures are interpreted and run in the sequence they appear in the SAS program. A SAS program requires the SAS software to run.

Analytics
SAS held a 35.2 percent market share for advanced analytics as of 2010, more than twice that of the second largest share owner. SAS’ traditional strengths are bringing traditional and advanced analytics closer together.

SAS is best known for its role in predictive analytics. SAS’s predictive analytics and data mining were evaluated by Forrester against 53 criteria in three categories. SAS earned top overall ranking in all three categories, including perfect scores for functionality, professional services, licensing and cost, direction, and company financials.

Business Intelligence
SAS is number three in terms of worldwide market share by revenue in the Business Intelligence (BI) market. The company had 11 percent of the BI market as of 2010.

SAS Institute has grown mostly organically, with fewer acquisitions than other larger software vendors. As a result, its BI products are better integrated and SAS can almost fully concentrate on innovation rather than integration.

Data Management
SAS Data Management includes data integration, data quality, master data management and enterprise data access products. A 124-point review by Forrester found that DataFlux (a SAS subsidiary) stood out for its ability to generate customer loyalty through product ease of use, managing pricing complexity, effectively meeting and exceeding customer expectations, and delivering a positive account management experience. SAS is in the Leaders Quadrant for the Gartner 2011 Data Integration Tools Magic Quadrant.

Criticisms
In Progress

Features
In Progress