Predictive modeling is all the rage these days. However, end users and data scientists have very different ideas about what predictive models truly are.
Predictive modeling is all the rage these days. However, end users and data scientists have very different ideas about what predictive models truly are. With analytics becoming the buzz word and machine learning gaining widespread recognition, there is a tendency to view it as a magic wand, a panacea for all the analytics problems that a spiteful life throws at us. Data scientists are often asked about how to make their predictive models more accurate and whether newer algorithms can help improve the quality of their models. The answer to that question, as to most complex questions is - it depends. There really is no one size fits all where the accuracy of predictive models is concerned. Engineering problems, which are fairly well defined, require accuracies as high as 99% or above. In contrast, biologists dealing with complex systems seem to be deliriously happy if they approach an accuracy of around 75%. Given this wide disparity, there is a lot of confusion among folks trying to understand what predictive modeling is all about. My attempt here is to try and dispel a few myths regarding the same. http://www.predictiontracking.com/home/you-cana-t-predict-a-black-swan.html
Myth 1: Machine learning can predict anything - Well no. Machine learning approaches are dependent on the data input to the system. They can learn from the data and use it to predict the future provided that future is part of the dataset used to learn the model. Nassim Nicholas Taleb, in his book The Black Swan illustrates this with the example of someone trying to predict the health of a turkey in the US, given only the information for the previous days. Let us assume the person starts predicting at the beginning of the year. His predictions are going to be about the continued health of the turkey. On the Thanksgiving Day, however, his prediction is going to be horrendously wrong since nothing in the data he had accumulated had anything remotely similar to such an event. Hence, the model would fail to predict the death of the turkey on Thanksgiving Day. So the first lesson is that predictive models can't predict what is not present in the training data.
Now, this can be depressing to folks who have looked at predictive modeling as a magic wand. So what can these models predict then? There are plenty of things that predictive models can do as long as we understand their limitations. The only approach that would work would be to build the model using data from previous years. A machine learning algorithm would then be able to account for the sudden demise of the turkey on that particular day. It is all about the data.
Myth 2: Complicated algorithms can help to improve accuracies - It is generally a rookie mistake to assume that if we were to take a data set that we have and use more complicated algorithms to learn from it, our model accuracies are going to be better. Given the state of the machine learning algorithms now, the accuracies for most models will fall within a few percentage points of each other. Algorithmic complexity can never provide enough cover for bad data. As the old adage goes, 'Garbage in garbage out', and it is completely applicable to predictive modeling as well.
Myth 3: We need to use as much data as we can get - What we need is not large volumes of data but large volumes of relevant data. For example, if we were trying to build a predictive model on employee churn, we might need employee performance data, rewards and recognition data, compensation, pay grades, age, experience, tenure, leaves taken, distance from work and educational details to start with.
Myth 4: Once we have the data we are guaranteed a good model - Having data is no guarantee of a successful predictive model. Hence, before model building it is essential to conduct exploratory data analysis and identify correlations of the different variables with the dependent variable (churn in this case) to see if there really is any point in even building the model. Choice of the right variables (also called feature or variable selection) becomes extremely critical for building the right model.
Myth 5: A model once built is applicable for all time - Life is not constant. Things change and so does the applicability of a predictive model. If the demographic profile of your organization changes, chances are that the predictive attrition model that was so lovingly built a year ago would be completely useless at predicting attrition in the current population. Hence, as new data comes in, models need to be rebuilt.
As you can see, predictive modeling is an art as well as a science. Understanding the limitations of these approaches is critical before we can start thinking about implementing them in our organizations.
The psychology of luck: how superstition can help you win.
Why do so many Americans believe in luck against all reason? Psychologists tell us that sometimes, feeling lucky can actually improve performance.
The intensive weight lifting and strength training that bodybuilders undergo changes their bodies, making them stronger and leaner. Building muscle mass is not only healthy in the short term, but can also have long-lasting health benefits. For example, according to LiveStrong, with age comes a loss of muscle mass and strength attributed to sarcopenia, the natural and normal decline in muscle. Building up muscle mass earlier in life can help to slow down this natural muscle decline, keeping your stronger for longer. In the long term, it can help you to live independently and maintain a better quality of life in your later years, though it does come with some potential downsides.
When done correctly, bodybuilding can be very beneficial to your overall health.
Drug companies are using several strategies to get more people to participate in clinical trials. Among the ideas: A partnership with Lyft to get people to labs. Some companies sift through laboratory-test records to identify people with certain diseases who might qualify for drug trials. Other firms monitor how patients discuss their diseases in online forums to develop effective recruitment approaches. Drug trials are crucial to the introduction of new medicines, but they depend on companies getting enough patients to volunteer. Regulators require the studies to determine if a compound works safely in subjects and should be approved. Trial subjects are closely monitored at study research sites to see if the drug is proving more effective than a placebo or a medicine currently in use, without undue side effects. Often, doctors who are helping conduct the research ask their own patients who meet a trial’s criteria to join. Some research sites advertise on TV, radio and online looking for recruits. The number of participants needed for a trial varies widely.
Dr. Gene Beresin, a psychiatrist and Executive Director of The Clay Center for Young Healthy Minds at Massachusetts General Hospital, says 50% to 60% of college students have a psychiatric disorder. “What I’m including in that is the use of substances, anxiety, depression, problems with relationships, break-ups, academic problems, learning disabilities, attentional problems,” says Dr. Beresin. “If you add them all up 50% doesn’t seem that high.” Dr. Beresin says the suicide rate in college in astronomical. “A college student kills himself every day,” he says. Dr. Beresin says the brain doesn’t fully mature until age 26 so college students are put in a difficult situation. “Living alone, not being prepared to be on your own,” says Dr. Beresin. “Peer pressure. I mean, the ability to kind of freely use alcohol or drugs and make those decisions on your own without supervision.”
Grads make more money in virtually every discipline, but gender gap remains.
According to the Education Policy Research Initiative at the University of Ottawa, higher education is linked to higher salaries almost regardless of the subject.
FMRI scans show dogs recognize both words themselves and tone in which they're spoken.
Model can help forest managers better maintain forests by predicting which trees will survive.
Scientists have identified an inner ear deficiency in children with autism that may affect their ability to recognize speech. The finding suggests that a hearing test could one day be used identify children at risk for the disorder at an early age.
“This technique may provide clinicians a new window into the disorder and enable us to intervene earlier.”
The author of Sapiens, a new history of humankind, says technology is transforming us from biological creatures to something akin to bionic cyborgs. Humans – homo sapiens – rule the world. For better or worse, some might say. Historian Yuval Noah Harari looks at how that happened – why – and where we’re headed next. It’s us and not others, he says, because of our affinity for myth-making and stories. We buy into big ideas that bind us together and have given us power. Religion. Money. Nation states. Now that power may threaten the planet. But evolution isn’t over. Homo sapiens may be in their last few hundred years, he says. Ready to merge with machines. The gap between power and happiness. We are thousands of times more powerful than our ancestors. But if you look at it from the viewpoint of our ancestors it isn’t clear that we are a thousand times happier than they were. It is the most important and disturbing lesson of history. Especially in the 21st century as we gain more power. It isn’t clear that all this power will make the world a happier place.