5月 312018
 

If you’re considering upgrading to SAS Visual Analytics 8.2 or adding the product to the list of SAS products you’re currently using, you now have any easy way to see what SAS Visual Analytics (VA) 8.2 is all about. SAS Visual Analytics Interactive Demos allow you to access the interface and product instantly. Simply choose a report to navigate and explore in our SAS Visual Analytics 8.2 viewer.

Check out the following reports:

Warranty Analysis

Warranty costs are a huge expense for global manufacturers, and high-profile product recalls are in the headlines regularly. Product quality has become an important differentiator, and that makes it more critical than ever to communicate accurate warranty information throughout the organization.

Interactive reports with SAS Visual Analytics

This interactive demo allows you to see how SAS Visual Analytics can enable you to:

  • Analyze warranty claims to identify potential issues – and their underlying causes – fast.
  • Use that valuable information to address issues proactively, before they become costly problems.

Retail Insights

With competition at an all-time high, retailers everywhere seek stronger customer relationships, more profitable growth and a unique competitive advantage. Better understanding performance and making data-driven decisions have become essential.

This interactive demo illustrates how SAS Visual Analytics can provide valuable retail insights by enabling you to:

  • Analyze store performance on a regional basis.
  • Use what-if scenario building to make decisions on store locations and modifications.
  • Ensure the success of promotions by comparing actual revenue to forecast and baseline revenue.

Water Consumption and Quality

To effectively manage the consumption and monitor the quality of our most precious natural resource, utilities need to view water consumption patterns in different ways and drill into the details of that analysis. To ensure water quality, specific metrics must be monitored at regular intervals.

This interactive demo shows how SAS Visual Analytics enables you to:

  • Analyze water consumption data to reveal usage patterns so you can identify properties with potential water leaks or candidates for water reduction initiatives.
  • Visualize data from various water quality sensors, and apply statistical correlation to identify relationships between different quality metrics, which takes the guesswork out of your analysis.

Banking and Risk Insights

Financial institutions of all sizes often struggle to make sense of complex relationships within their portfolios and across holding companies, and to manage associated risks effectively. To better manage exposures, make well-informed decisions, and comply with regulatory mandates, banks need a way to quickly understand their risk – and the potential impacts of changing market conditions – across holding companies, subsidiaries and lines of business.

This interactive demo illustrates how SAS Visual Analytics provides a holistic view of bank performance across regions, down to an individual counterparty level, enabling you to:

  • View and analyze returns by industry and geography.
  • Analyze and explore the capital exposure of different banks.
  • View concentration risk across banks and counterparties, and drill down to view a counterparty's economic capital, returns and expected loss.
  • Compare RAROC and exposure over time for each line of business and industry, and assess the bank's capacity to handle stress and operate profitably.

Network Performance

Not all cell towers or handsets are created equal. And customer consumption patterns are as individual as the customers themselves. Yet all these factors have a direct impact on network service performance. Finding the right mix of traffic to optimize an individual customer’s experience is essential to a carrier’s brand – but it’s not easy to do.

This interactive demo shows how SAS Visual Analytics lets you:

  • Analyze network usage from both a customer and network perspective.
  • Simultaneously monitor both a customer’s experience and an individual cell tower's performance so you can take prompt action to ensure that your brand’s reputation and customer loyalty remain high.

If you want to dive further into the software and learn how to build your own interactive reports, dashboards or simply evaluate self-service analytics capabilities using your own data, then you can sign up for a 14-day trial here.

Don’t forget to download or upgrade our SAS Mobile BI apps (iOS and Android), so you can view these SAS Visual Analytics 8.2 reports on the go wherever you are!

Exploring interactive reports with SAS Visual Analytics was published on SAS Users.

5月 312018
 

A previous article showed how to use a calibration plot to visualize the goodness-of-fit for a logistic regression model. It is common to overlay a scatter plot of the binary response on a predicted probability plot (below, left) and on a calibration plot (below, right):

The SAS program that creates these plots is shown in the previous article. Notice that the markers at Y=0 and Y=1 are displayed by using a scatter plot. Although the sample size is only 500 observations, the scatter plot for the binary response suffers from overplotting. For larger data sets, the scatter plot might appear as two solid lines of markers, which does not provide any insight into the distribution of the horizontal variable. You can plot partially transparent markers, but that does not help the situation much. A better visualization is to eliminate the scatter plot and instead use a binary fringe plot (also called a butterfly fringe plot) to indicate the horizontal positions for each observed response.

A predicted probability plot with binary fringe

A predicted probability plot with a binary fringe plot for logistic regression

A predicted probability plot with a binary fringe plot is shown to the right. Rather than use the same graph area to display the predicted probabilities and the observed responses, a small "butterfly fringe plot" is shown in a panel below the predicted probabilities. The lower panel indicates the counts of the responses by using lines of various lengths. Lines that point down indicate the number of counts for Y=0 whereas lines that point up indicate the counts for Y=1. For these data, the X values less than 1 have many downward-pointing lines whereas the X values greater than 1 have many upward-pointing lines.

To create this plot in SAS, you can do the following:

  1. Use PROC LOGISTIC to output the predicted probabilities and confidence limits for a logistic regression of Y on a continuous explanatory variable X.
  2. Compute the min and max of the continuous explanatory variable.
  3. Use PROC UNIVARIATE to count the number of X values in each of 100 bins in the range [min, max] for Y=0 and Y=1.
  4. Merge the counts with the predicted probabilities.
  5. Define a GTL template to define a panel plot. The main panel shows the predicted probabilities and the lower panel shows the binary fringe plot.
  6. Use PROC SGRENDER to display the panel.

You can download the SAS program that defines the GTL template and creates the predicted probability plot.

A calibration plot with binary fringe

A calibration plot with a binary fringe plot for logistic regression

By using similar steps, you can create a calibration plot with a binary fringe plot as shown to the right. The main panel is used for the calibration plot and a small binary fringe plot is shown in a panel below it. The lower panel shows the counts of the responses at various positions. Note that the horizontal variable is the predicted probability from the model whereas the vertical variable is the empirical probability as estimated by the LOESS procedure. For these simulated data, the fringe plot shows that most of the predicted probabilities are less than 0.2 and these small values mostly correspond to Y=0. The observations for Y=1 mostly have predicted probabilities that are greater than 0.5. The fringe plot reveals that about 77% of the observed responses are Y=0, a fact that was not apparent in the original plots that used a scatter plot to visualize the response variable.

To create this plot in SAS, you can do the following:

  1. Use PROC LOGISTIC to output the predicted probabilities for any logistic regression.
  2. Use PROC LOESS to regress Y onto the predicted probability. This estimates the empirical probability for each value of the predicted probability.
  3. Use PROC UNIVARIATE to count the number of predicted probabilities for each of 100 bins in the range [0, 1] for Y=0 and Y=1.
  4. Merge the counts with the predicted probabilities.
  5. Define a GTL template to define a panel plot. The main panel shows the calibration plot and the lower panel shows the binary fringe plot.
  6. Use PROC SGRENDER to display the panel.

You can download the SAS program that defines the GTL template and creates the calibration plot.

For both plots, the frequencies of the responses are shown by using "needles," but you can make a small change to the GTL to make the fringe plot use thin bars so that it looks more like a butterfly plot of two histograms. See the program for details.

What do you think of this plot? Do you like the way that the binary fringe plot visualizes the response variable, or do you prefer the classic plot that uses a scatter plot to show the positions of Y=0 and Y=1? Leave a comment.

The post Use a fringe plot to visualize binary data in logistic models appeared first on The DO Loop.

5月 312018
 

Called out as two common IT threads in my December blog post, how do artificial intelligence and automation connect with another prominent movement, the Internet of Things (IoT)? First, consider these 2017 predictions in the IDC FutureScape on IoT. By 2019, At least 40 percent of IoT-created data will be stored, processed, analyzed [...]

Toward the artificial intelligence of things was published on SAS Voices by Oliver Schabenberger

5月 302018
 

developing foolproof solutionsAs oil and water, hardware and software don't mix, but rather work hand-in-hand together to deliver value to us, their creators. But sometimes, we make mistakes, behave erratically, or deal with others who might make mistakes, behave erratically, or even take advantage of our technologies.

Therefore, it is imperative for developers, whether hardware or software engineers, to foresee unintended (probable or improbable) system usages and implement features that will make their creations foolproof, that is protected from misuse.

In this post I won’t lecture you about various techniques of developing foolproof solutions, nor will I present even a single snippet of code. Its purpose is to stimulate your multidimensional view of problems, to unleash your creativity and to empower you to become better at solving problems, whether you develop or test software or hardware, market or sell it, write about it, or just use it.

You May Also Like: Are you solving the wrong problem?

The anecdote I’m about to tell you originated in Russia, but since there was no way to translate this fictitious story exactly without losing its meaning, I attempted to preserve its essence while adapting it to the “English ear” with some help from Sir Arthur Conan Doyle. Well, sort of. Here goes.

The Art of Deduction

Mr. Sherlock Holmes and Dr. Watson were traveling in an automobile in northern Russia. After many miles alone on the road, they saw a truck behind them. Soon enough, the truck pulled ahead, and after making some coughing noises, suddenly stopped right in front of them. Sherlock Holmes stopped their car as well.

Dr. Watson: What happened? Has it broken?

Holmes: I don’t think so. Obviously, it ran out of gas.

The truck driver got out of his cabin, grabbed a bucket hanging under the back of the truck and ran towards a ditch on the road shoulder. He filled the bucket with standing water from the ditch and ran back to his truck. Then, without hesitation, he carefully poured the bucketful of water into the gas tank. Obviously in full confidence of what he’s doing, he returned to the truck, started the engine, and drove away.

Dr. Watson (in astonishment): What just happened? Are Russian ditches filled with gasoline?

Holmes: Relax, dear Watson, it was ordinary ditch water. But I wouldn’t suggest drinking it.

Dr. Watson (still in disbelief): What, do their truck engines work on water, then?

Holmes: Of course not, it’s a regular Diesel engine.

Dr. Watson: Then how is that possible? If the truck was out of gas, how was it able to start back up after water was added to the tank?!

Who knew Sherlock Holmes had such engineering acumen!

Holmes: “Elementary, my dear Watson. The fuel intake pipe is raised a couple inches above the bottom of the gas tank. That produces the effect of seemingly running out of gas when the fuel falls below the pipe, even though there is still some gas left in the tank. Remember, oil and water don't mix.  When the truck driver poured a bucketful of water into the gas tank, that water – having a higher density than the Diesel fuel – settled in the bottom, pushing the fuel above the intake opening thus making it possible to pump it to the engine.”

After a long pause – longer than it usually takes to come to grips with reality – Dr. Watson whispered in bewilderment.

Dr. Watson: Я не понимаю, I don’t understand!

Then, still shaken, he asked the only logical question a normal person could possibly ask under the circumstances.

Dr. Watson: Why would they raise the fuel intake pipe from the tank bottom in the first place?

Holmes: Ah, Watson, it must be to make it foolproof. What if some fool decides to pour a bucket of water in the gas tank!

You May Also Like: Are you solving the wrong problem?

Are you developing foolproof solutions? was published on SAS Users.

5月 302018
 

Remember when electric vehicles were a new thing? Just a few years ago, everywhere we turned there were opinions, white papers, and articles espousing the wonders of electric vehicles, and an equal chorus of voices warning of the dangers and challenges of electric vehicles. Would they blow up half of [...]

How will electric vehicles contribute to the smart grid? was published on SAS Voices by Mike F. Smith

5月 302018
 

According to a recent Bloomberg article, this year the United States passed Hong Kong and Singapore to become the country with the world's most competitive economy! They say, "The U.S. dethroned Hong Kong to retake first place among the world's most competitive economies, thanks to faster economic growth and a [...]

The post Which country has the world's most competitive economy? appeared first on SAS Learning Post.

5月 302018
 

Why does your organization’s website or mobile app exist? What are you hoping to accomplish with your business by being digital? What are the most important priorities for your digital presence? Here are three goals that most organizations share: Sell more stuff. Make marketing more effective. Delight customers. Goals are [...]

SAS Customer Intelligence 360: Goals, propensity models, and machine learning was published on Customer Intelligence Blog.

5月 302018
 

Maybe you’ve heard of text analytics (or natural language processing) as a way to analyze consumer sentiment. Businesses often use these techniques to analyze customer complaints or comments on social media, to identify when a response is needed. But text analytics has far more to offer than examining posts on [...]

5 remarkable uses for text analytics was published on SAS Voices by Tom Sabo

5月 302018
 

SAS Enterprise Miner has been a leader in data mining and modeling for over 20 years. The system offers over 80 different nodes that help users analyze, score and model their data. With a wide range of functionalities, there can be a number of different ways to produce the results you want.

At SAS® Global Forum 2018, Principal Systems Engineer Melodie Rush spoke about her experience with SAS® Enterprise Miner™, and compiled a list of hints that she believe will help users of all levels. This article previews her full presentation, Top 10 Tips for SAS Enterprise Miner Based on 20 Years’ Experience. The paper includes images and further details of each of the tips noted below; I’d encourage you to check it out to learn more.

Top Ten Tips for Enterprise Miner

Tip 1: How to find the node you’re looking for

If you struggle finding the node that best fits what you need, there’s a system that can simplify it.

Nodes are organized by Sample, Explore, Modify, Model, and Assess. Find which of these best describes what you are trying to do, and scroll across each node alphabetically for a description.

Tip 2: Add node from diagram workspace

Double click any node on the toolbar to see its properties. An example of the results this presents are shown below:

Top Ten Tips for Enterprise Miner

Tip 3: Clone a process flow

Highlight process flow by dragging your mouse across, right-click or CTRL+C, and Paste or CTRL+V where you want to insert process flow.

Tip 4: New features

  • There’s a new tab, HPDM (High-Performance Data Mining), which contains several new nodes that cover data mining and machine learning algorithms.
  • There are two new nodes under Utility that incorporate Open Source and SAS Viya.
  • The Open Source Integration node allows you to use R language code in SAS Enterprise Miner diagrams.
  • A SAS Viya Code node now incorporates code that will be used in SAS Viya and CAS, and algorithms from SAS Visual Data Mining and Machine Learning.
  • To save and share your results, there are now the Register Model and Save Data nodes under Utility.
  • You can now register models to the SAS Metadata Server to score or compare easily.
  • A Save Data node lets you save training, validation, test, score, or transaction data as SAS, JMP, Excel, CSV or tab-delimited files.

Tip 5: The unknown node

The reporter node under Utility allows you to easily document your Enterprise Miner process flow diagrams. A .pdf or .rtf is created with an image of the process flow.

Tip 6: The node that changes everything

The Metadata node, on the Utility tab, allows you to change metadata information and values in your diagram. You also can capture settings to then apply to data in another diagram.

Tip 7: How to generate a scorecard

A scorecard emphasizes what variables and values from your model are important. Values are reported on a 0 to 1,000 scale, with the higher being more likely the event you’re measuring occurs. To do this, have the Reporter node follow a Score node, and then change the Nodes property to Summary under Reporter node properties.

Tip 8: How to override the 512 level limit

If faced with the error message, “Maximum target levels of 512 exceeded,” your input is resulting in more than 512 distinct results. To get around this, you need to change EM_TRAIN_MAXLEVELS to another value. To do so, either change the macro value in properties

or change the macro value in project start code.

Tip 9: Which variable selection method should I use?

Instead of choosing just one variable selection method, you can combine different ones such as Decision Trees, Forward, Chi-Square, and others. The results can be combined using different selection properties, such as None (no changes made from original metadata), Any (reject a variable if any previous variable selection nodes reject it), All (reject a variable if all of the previous variable selection nodes reject it), and Majority (reject a variable if the majority of the variable selection nodes reject it).

Tip 10: Interpreting neural network

Decision trees can be produced to interpret networks, by changing the Prediction variable to be your Target and the Target variable to be rejected.

Conclusion

With so many options to create models that best suit your preferences, these tips will help sharpen your focus and allow you to use SAS Enterprise Miner more efficiently and effectively. This presentation was one in a series of talks on Enterprise Miner tool presented at SAS® Global Forum 2018.

Additional Resources

SAS Enterprise Miner
SAS Enterprise Learning Tutorials
Getting Started With SAS Enterprise Miner Tutorial Videos

Additional SAS Enterprise Miner talks from Global Forum 2018

A Case Study of Mining Social Media Data for Disaster Relief: Hurricane Irma
Bogdan Gadidov, Linh Le, Analytics and Data Science Institute, Kennesaw State University

A Study of Modelling Approaches for Predicting Dropout in a Business College
Xuan Wang, Helmut Schneider, Louisiana State University

Analysis of Nokia Customer Tweets with SAS® Enterprise Miner™ and SAS® Sentiment Analysis Studio
Vaibhav Vanamala MS in Business Analytics, Oklahoma State University

Analysis of Unstructured Data: Topic Mining & Predictive Modeling using Text
Ravi Teja Allaparthi

Association Rule Mining of Polypharmacy Drug Utilization Patterns in Health Care Administrative Data Using SAS® Enterprise Miner™
Dingwei Dai, Chris Feudtner, The Children’s Hospital of Philadelphia

Bayesian Networks for Causal Analysis
Fei Wang and John Amrhein, McDougall Scientific Ltd.

Classifying and Predicting Spam Messages Using Text Mining in SAS® Enterprise Miner™
Mounika Kondamudi, Oklahoma State University

Image Classification Using SAS® Enterprise Miner 14.1

Model-Based Fiber Network Expansion Using SAS® Enterprise Miner™ and SAS® Visual Analytics
Nishant Sharma, Charter Communications

Monte Carlo K-Means Clustering SAS Enterprise Miner
Donald K. Wedding, PhD Director of Data Science Sprint Corporation

Retail Product Bundling – A new approach
Bruno Nogueira Carlos, Youman Mind Over Data

Using Market Basket Analysis in SAS® Enterprise MinerTM to Make Student Course Enrollment Recommendations
Shawn Hall, Aaron Osei, and Jeremiah McKinley, The University of Oklahoma

Using SAS® Enterprise Miner for Categorization of Customer Comments to Improve Services at USPS
Olayemi Olatunji, United States Postal Service Office of Inspector General

Top 10 tips for SAS Enterprise Miner based on 20 years’ experience was published on SAS Users.

5月 302018
 

SAS Enterprise Miner has been a leader in data mining and modeling for over 20 years. The system offers over 80 different nodes that help users analyze, score and model their data. With a wide range of functionalities, there can be a number of different ways to produce the results you want.

At SAS® Global Forum 2018, Principal Systems Engineer Melodie Rush spoke about her experience with SAS® Enterprise Miner™, and compiled a list of hints that she believe will help users of all levels. This article previews her full presentation, Top 10 Tips for SAS Enterprise Miner Based on 20 Years’ Experience. The paper includes images and further details of each of the tips noted below; I’d encourage you to check it out to learn more.

Top Ten Tips for Enterprise Miner

Tip 1: How to find the node you’re looking for

If you struggle finding the node that best fits what you need, there’s a system that can simplify it.

Nodes are organized by Sample, Explore, Modify, Model, and Assess. Find which of these best describes what you are trying to do, and scroll across each node alphabetically for a description.

Tip 2: Add node from diagram workspace

Double click any node on the toolbar to see its properties. An example of the results this presents are shown below:

Top Ten Tips for Enterprise Miner

Tip 3: Clone a process flow

Highlight process flow by dragging your mouse across, right-click or CTRL+C, and Paste or CTRL+V where you want to insert process flow.

Tip 4: New features

  • There’s a new tab, HPDM (High-Performance Data Mining), which contains several new nodes that cover data mining and machine learning algorithms.
  • There are two new nodes under Utility that incorporate Open Source and SAS Viya.
  • The Open Source Integration node allows you to use R language code in SAS Enterprise Miner diagrams.
  • A SAS Viya Code node now incorporates code that will be used in SAS Viya and CAS, and algorithms from SAS Visual Data Mining and Machine Learning.
  • To save and share your results, there are now the Register Model and Save Data nodes under Utility.
  • You can now register models to the SAS Metadata Server to score or compare easily.
  • A Save Data node lets you save training, validation, test, score, or transaction data as SAS, JMP, Excel, CSV or tab-delimited files.

Tip 5: The unknown node

The reporter node under Utility allows you to easily document your Enterprise Miner process flow diagrams. A .pdf or .rtf is created with an image of the process flow.

Tip 6: The node that changes everything

The Metadata node, on the Utility tab, allows you to change metadata information and values in your diagram. You also can capture settings to then apply to data in another diagram.

Tip 7: How to generate a scorecard

A scorecard emphasizes what variables and values from your model are important. Values are reported on a 0 to 1,000 scale, with the higher being more likely the event you’re measuring occurs. To do this, have the Reporter node follow a Score node, and then change the Nodes property to Summary under Reporter node properties.

Tip 8: How to override the 512 level limit

If faced with the error message, “Maximum target levels of 512 exceeded,” your input is resulting in more than 512 distinct results. To get around this, you need to change EM_TRAIN_MAXLEVELS to another value. To do so, either change the macro value in properties

or change the macro value in project start code.

Tip 9: Which variable selection method should I use?

Instead of choosing just one variable selection method, you can combine different ones such as Decision Trees, Forward, Chi-Square, and others. The results can be combined using different selection properties, such as None (no changes made from original metadata), Any (reject a variable if any previous variable selection nodes reject it), All (reject a variable if all of the previous variable selection nodes reject it), and Majority (reject a variable if the majority of the variable selection nodes reject it).

Tip 10: Interpreting neural network

Decision trees can be produced to interpret networks, by changing the Prediction variable to be your Target and the Target variable to be rejected.

Conclusion

With so many options to create models that best suit your preferences, these tips will help sharpen your focus and allow you to use SAS Enterprise Miner more efficiently and effectively. This presentation was one in a series of talks on Enterprise Miner tool presented at SAS® Global Forum 2018.

Additional Resources

SAS Enterprise Miner
SAS Enterprise Learning Tutorials
Getting Started With SAS Enterprise Miner Tutorial Videos

Additional SAS Enterprise Miner talks from Global Forum 2018

A Case Study of Mining Social Media Data for Disaster Relief: Hurricane Irma
Bogdan Gadidov, Linh Le, Analytics and Data Science Institute, Kennesaw State University

A Study of Modelling Approaches for Predicting Dropout in a Business College
Xuan Wang, Helmut Schneider, Louisiana State University

Analysis of Nokia Customer Tweets with SAS® Enterprise Miner™ and SAS® Sentiment Analysis Studio
Vaibhav Vanamala MS in Business Analytics, Oklahoma State University

Analysis of Unstructured Data: Topic Mining & Predictive Modeling using Text
Ravi Teja Allaparthi

Association Rule Mining of Polypharmacy Drug Utilization Patterns in Health Care Administrative Data Using SAS® Enterprise Miner™
Dingwei Dai, Chris Feudtner, The Children’s Hospital of Philadelphia

Bayesian Networks for Causal Analysis
Fei Wang and John Amrhein, McDougall Scientific Ltd.

Classifying and Predicting Spam Messages Using Text Mining in SAS® Enterprise Miner™
Mounika Kondamudi, Oklahoma State University

Image Classification Using SAS® Enterprise Miner 14.1

Model-Based Fiber Network Expansion Using SAS® Enterprise Miner™ and SAS® Visual Analytics
Nishant Sharma, Charter Communications

Monte Carlo K-Means Clustering SAS Enterprise Miner
Donald K. Wedding, PhD Director of Data Science Sprint Corporation

Retail Product Bundling – A new approach
Bruno Nogueira Carlos, Youman Mind Over Data

Using Market Basket Analysis in SAS® Enterprise MinerTM to Make Student Course Enrollment Recommendations
Shawn Hall, Aaron Osei, and Jeremiah McKinley, The University of Oklahoma

Using SAS® Enterprise Miner for Categorization of Customer Comments to Improve Services at USPS
Olayemi Olatunji, United States Postal Service Office of Inspector General

Top 10 tips for SAS Enterprise Miner based on 20 years’ experience was published on SAS Users.