Predictive Analytics

“The truth is that data embodies a priceless collection of experience from which to learn.”

Key takeaway

Data is taking experiences and converting them to numbers. We can learn from this numbers just like we learn from experiences

“As data piles up, we have ourselves a genuine gold rush. But data isn’t the gold. I repeat, data in its raw form is boring crud. The gold is what’s discovered therein.”

Key takeaway

Data is not an insight. WHat you do with the data is the gold

“But all predictive models share the same objective: They consider the various factors of an individual in order to derive a single predictive score for that individual. This score is then used to drive an organizational decision, guiding which action to take.”

Key takeaway

When you are aware of your biases and prejudices, you are applying Bayesian theory to your predictions. Predictive modeling is attempting to generate a score for each person based on their data

“This was ironic, since all predictive modeling is a kind of reverse engineering to begin with. Machine learning starts with the data, an encoding of things that have happened, and attempts to uncover patterns that generated or explained the data in the first place.”

Key takeaway

Looking at data to solve problems is similar to reverse engineering

“The notion of assembling components into a more complex, powerful structure is the very essence of engineering, whether constructing buildings and bridges or programming the operating system that runs your iPhone.”

Key takeaway

Breaking things down simply then building them back up is the very nature of an engineer/scientist

“The ensemble effect: when joined in an ensemble, predictive models compensate for one another’s limitations, so the ensemble as a whole is more likely to predict correctly than its component models are.”

Key takeaway

Similar to what Nate Silver said, the whole is greater than the sum of its parts

“Predicting impact impacts prediction. PA shifts substantially, from predicting a behavior to predicting influence on behavior. Predicting influence promises to boost PA’s value, since an organization doesn’t just want to know what individuals will do-it wants to know what it can do about it. It makes predictive scores actionable.”

Key takeaway

If you can predict influence on behavior then you know what actions to take to execute

“Uplift model - a predictive model that predicts the influence on an individual’s behavior that results from applying one treatment over another.”

Key takeaway

Predicting influence is better for a business than just predicting behavior

“Just as with medicine, marketing’s success-or lack thereof- is revealed by comparing to a control set, a group of individuals suppressed from the treatment )or administered a placebo, in the case of medicine). Therefore, we need to collect two sets of data.”

Key takeaway

you need a placebo to truly measure if it worked or not by giving it a comparison. Placebo effect is key to marketing as is A/B testing

“For U.S. Bank, response uplift modeling delivered an unprecendented boost, increasing the marketing campaign’s return on investment by a factor of five in comparison with standard response model targeting This win resulted from decreasing both the amount of direct mail that commanded no impact and the amount that instigated an adverse response.”

Key takeaway

There are two ways to grow: increase conversion or decrease churn

“You want power? True power comes in influencing the future rather than speculating on it. Nate Silver publicly competed to win election forecasting, while Obama’s analytics team quietly comepeted to win the election itself. This reflects the very difference between forecasting and predictive analytics. Forecasting calculates an aggregate view for each U.S. state, while predictive analytics delivers action-oriented insight: predictions for each individual voter.”

Key takeaway

Forecasting is speculation while PA is actionable insight