The Modeling Agency logo

Analytics Transformed™
  • This field is for validation purposes and should be left unchanged.

Posts Tagged ‘data mining’

Predictive Analytics Helps Change the Face of Recalls

AutoRecallsThere are few events more costly to a business than a recall. The costs in terms of lost time, lost money, and lost public trust can be staggering.

And, of course, nobody wants to put consumers in danger.

Fortunately, predictive analytics has changed all that. According to Automotive News, data mining has just helped GM limit a recall to just 4 cars.

That’s right, four cars.

In the past, the auto maker might have recalled the model and inconvenienced tens of thousands of owners, despite thinking just a few cars had the defect. Or it might have let the defect slide, putting a few customers at risk of a crash.

But…[when]…a 2012 Chevrolet Volt was brought in for a warranty repair in Europe, General Motors had a third, better option.

On May 30, the auto maker assigned the engineer to dig into a data base that tracks the parts used in its cars, and it collected manufacturing records from the supplier–in this case, TRW Automotive. Within a month, GM had identified [all 4]…of the cars on US soil with the faulty valve, called the owners and sent a formal notice to the US Government.

…Maureen Foley-Gardner, director of field performance evaluation at GM, said the auto maker had used its database for 20 percent of field actions this year, up from 5 percent in 2012, and watched as the average action has shrunk by 40%.

This development is poised to save the auto industry a staggering $50 billion per year. And, as the article goes on to note, this accomplishment only scratches the surface of the kinds of problems that auto companies are solving every single day when they use data mining the right way.

If you’d like to start seeing big results in your business then it’s time to get the training that you need to use data mining correctly. Start with TMA’s free webinar, then move on to The Modeling Agency’s advanced training courses.

Which problems will you solve today?

Data Mining Helps Dannon Yogurt Increase Market Share

YogurtThe Dannon Company is using data analysis to make excellent business decisions. The company’s data mining efforts were recently featured in this article from

Like retailers, Dannon uses the data (gathered from store shelves and not directly from consumers) to take the guesswork out of making customers happy.

“Dannon works with retailers across the country to make sure their shelves are filled with the precise product volume and promotion for each store location to meet shopper demand…Through the use of predictive analysis, Dannon is able to understand, plan, and predict their business in ways that were unimaginable a few years ago.”

As the article pointed out, this type of analysis is particularly helpful because yogurt has a very limited shelf life. Success in the yogurt industry therefore means taking advantage of just-in-time supply and delivery. The company must be careful to avoid overstocking and under-stocking, since being too conservative could lose crucial sales.

It’s easy to extrapolate how other companies in the food industry (from suppliers, to food retailers, to restaurants) could benefit from this type of work, since all food has some kind of shelf life. Reducing or preventing waste is always a concern.

Dannon’s success also demonstrates how important it is for each business to isolate and track the right factors. There are a myriad of things you could track and measure, but only some of those parameters will actually lead you to information that will help you make good business decisions.

Good data analysis takes good training. That’s why The Modeling Agency offers a free data analysis webinar as well as a host of other predictive analysis training courses. Better training means better results and an increased data analysis ROI, so sign up today.

Data Analysis, Predicting the Weather, and Business Decisions

ThunderstormMany people believe that weather impacts us only when it is severe. However, weather impacts people and businesses in a myriad of other ways.

Some of the ways that weather impacts business are obvious. For example, food prices go up after a rash of bad hail, drought, or extreme heat.

Some of those impacts are less obvious. Retail sales can plummet when the weather is bad because nobody wants to be out in the middle of a storm.

The science of weather prediction itself is getting better. National Geographic outlined NOAA’s improved hurricane forecasting software quite recently.

Business is finding ways to turn improved weather data to its advantage. This CNBC report titled “Big Data Companies Try to Outwit Mother Nature’s Chaos” outlines some of those methods.

“While it’s still virtually impossible to predict an event like [the Oklahoma tornado,] the models and forecasts from big data companies can be extremely valuable to a variety of businesses, ranging from retailers to insurers, as they plan ahead.

Earth Risk, for example, focuses on the energy trading market. By focusing in on probability models for extreme heat and extreme cold it can help investors profit in the futures market.

[John Plavan, co-founder and CEO of Earth Risk Technologies] points to the winter of 2011-12, which many traders in the natural gas market expected to be cold, driving up futures prices. Earth Risk’s models, though, showed that the atmosphere wasn’t setting itself up for a high probability of cold weather, letting clients position themselves to make money when natural gas prices declined.”

Some private weather prediction models may even have an edge on NOAA. For example, IBM’s “Deep Thunder” draws its data from multiple sources, including NOAA itself. It also uses Earth Networks, NASA, and the U.S. Geological Survey.

If weather has an impact on your business it is a good idea to learn more about data mining and its many uses. TMA offers a variety of data analytics training courses to help companies learn how to use these powerful tools. Get started with TMAs’ free webinar today.

Data Mining Reduces Fraud, Combats Waste

FraudData mining typically provides some staggering returns on investment, especially when it comes to preventing theft, fraud, and other forms of waste. For hard numbers which back up this statement one has only to look to the ways that federal, state, and local governments plan to use data mining in the near future.

The numbers came up in this article which discusses new laws allowing Medicaid Fraud Control Units to use data mining in ways that will help them spot patterns of abuse. The article also helps to demonstrate how more people and institutions are starting to embrace the useful, helpful elements of this science.

Here’s what the Office of the Inspector General had to say about the new law. Note the expected ROI for government institutions:

“The OIG said that it expects that federal and state governments will spend a collective $12.3 million on data mining activities during the next decade, activities that it predicts will help recover $71.9 million during the same period, for a total savings of $58.9 million over 10 years.”

Data mining has long been used for loss prevention purposes in the private sector, particularly in the retail industry. Sophisticated programs can help spot employee theft as well as conditions which encourage shoplifting.

Almost every organization is vulnerable to some kind of fraud or abuse, so it pays to take these two examples to heart.

If your organization is ready to unleash the incredible power of data mining then it may be time to invest in data analysis training. Start with TMA’s free webinar, then move on to other data analytics training courses.

In a World Where Data Analysis Predicts Blockbusters

ClapperThe New York Times recently ran an article on the ways data mining is being used in Hollywood to predict sales at the box office. It turns out that there are some tangible factors that pop up in movies that do well vs. those that receive two-thumbs-down from moviegoers.

The industry leader in this enterprise is former statistics professor Vinny Bruzzese.

“Demons in horror movies can target people or be summoned,” Mr. Bruzzese said in a gravelly voice, by way of example. “If it’s a targeting demon, you are likely to have higher opening-weekend sales than if it’s summoned, so get rid of that Ouija Board scene.”

“Bowling scenes tend to pop up in films that fizzle…Therefore it’s statistically unwise to include one in your script. A cursed superhero never sells as well as a guardian superhero, one like Superman who acts as a protector.”

The average Hollywood film costs over $60 million to produce. It stands to reason that execs would want to have some guidance about what works and what doesn’t before investing any money into a film.

Bruzzese’s example only helps to demonstrate how data mining can help isolate what customers really like and want. That means that they have a better experience because companies can then deliver without messy guesswork.

Of course, there are some people who fear that this means that we’ll all be stuck in a world of bland products (and movies). But these fears are unfounded. Data mining is only a tool.

There are a lot of different ways to write movies with targeting demons and guardian superheroes, after all.

The Modeling Agency offers companies the training they need to make the most of advances in data mining no matter what their industry is. Start with TMA’s free webinar, and then move on to other data analysis training courses here.