Friday, April 5, 2013

Supermarket can Predict if its Customers are Pregnant




How can supermarket Target find out which customers are pregnant based on their buying habits?

Charles Duhigg wrote a book called The Power of Habit which explained how Target had successfully created a Pregnancy-prediction algorithm to predict its female customers pregnant or not. If you are interested, please read the book.

Andrew Pole, a statistician working for Target, has developed a Pregnancy-Prediction Algorithm in order to predict if women are pregnant or not. By analyzing Target’s customer database, Target has found out several shopping patterns which are specific for pregnant women, below lists out their shopping patterns:


  • Unscented lotion
  • Vitamin
  • Soap and cotton balls
  • Scent-free soap
  • Hand sanitizers
  • Wash Clothes

After discovering pregnant women among its customers, Target can send those expectant mothers customized coupons in order to boost sales.






 

Tuesday, April 2, 2013

Big Data for Small and Medium-Sized Companies



Big Data has gained increasing attention in IT and business world. But what is Big Data? Can Small and Medium-Sized Companies get benefits from utilization of Big Data? What is the business values derived from analyzing Big Data?

According to Rebecca Shockley , Global Research Leader for Business Analytics at the IBM Institute for Business Value, defined Big Data as “Big data is quite simply data that cannot be managed or analyzed by traditional technologies” and “So what is considered big data for one company may be different for another company. ‘Big’ doesn’t have to be really that big; it’s just bigger than what you’re used to dealing with.” So now you see that Big is more like a relative term.

Large corporations such as Amazon and PayPal have their own data scientists to take care of Big Data. However, utilization of Big Data is not just confined to large companies, instead Small and Medium-Sized Companies can get benefits from analyzing their own Big Data because the world has become more digital which means that more data is available easily. In other words, every company has their Big Data to handle with. One of the tools used to analyze Big Data is Data Mining. To know more about how Data Mining can be applied to your data, you can read  What is Data Mining or Condaho Predictive Business Analysis.

More and more companies have started to extract business insights from Big Data. For example, online retailers are on the front such as creating personal profile of their customers, offering dynamic pricing, identifying fraud cases or doing predictive analytics about their customer behaviors.

There is an article about Big Data on Swedish Newspaper Site (www.svd.se), the topic is about how Big Data predicts future. To read more, click here. 


Monday, April 1, 2013

What is Data Mining?

 What is data mining? 
I have been asked this question many times. Time to get to know about Data Mining. However, Data Mining is an interdisciplinary subject including statistics, machine learning etc, therefore, it can be defined in many different ways. One thing for sure is that it is nothing related to mining industry, except that they apply data mining techniques to their data.

Witten and Frank defined data mining as the process of discovering patterns in data.
Han, Kamber, Pei defined data Mining as one of the steps in the process of knowledge discovery and those steps of knowledge discovery are : 
  • Data Cleaning & Integration
  • Data Selection & Transformation
  • Pattern Evaluation
  • Knowledge Presentation

Regardless of different definitions, the purpose of Data Mining is to find some useful and important patterns ( insights) among data, which can become competitive advantage for companies, from getting to know their customers better to making better decisions.

What are major tasks of Data Mining?
Data Mining can be divided into 2 categories, which are descriptive data mining and predictive data mining. The former presents the data in summary, while the other creates one or a set of models which performs inference on the data and predict it on a new set of data.  The techniques of Data Mining include classification, clustering and association. To read more about it, please click What is Data Mining.






Thursday, March 28, 2013

What empowers predictive analytics?

 What is predictive analytics? Harriot wrote an article about predictive analytics. He briefly mentioned how predictive analytics could be applied in the business world, especially sales and marketing department such as prediction of customer behaviors. However, he did not mention what empowers predictive analytics. Data Mining is one of driving forces in predictive analytics. In near future, I will write some posts about how Data Mining has been applied to our daily lives without that we notice it.






Wednesday, March 27, 2013

7 Driving Forces of Retail Analytics


Do you want to know  7 driving forces of retail analytics in the future? Mind Wave created a video to explain those 7 forces including:

Mystery Shopping
Voice of Customers
Opinion Mining
ERP / Data Warehouse
RFID
WIFI
APP

Although those 7 forces are not something new, it might explain again that the future of analysis ( I believe not just in retail) will lie in the integration of difference sources.











Tuesday, March 26, 2013

Longer or wider dataset ?


  Should we have longer datasets or wider datasets? In other words, should we have more instances or more variables? Graham Forsyth wrote an article called 'Data: It’s not the length; it’s the width that matters!'. By the title, you can tell that he is on the variable side (horizontal approach). If you are interested, you can read the article. The reason I posted this article is because he pointed out an important issue of how we can optimize the length and width of datasets in  the wave of big data.
 







Monday, March 25, 2013

PayPal's Chief Data Scientist


Reading an article written by Dan Woods about PayPal’s Chief Scientist, Mok Oh. It is very interesting and I have summed up the article in this post, but if you want to read the details of the original article, please click here.

Who is Mok Oh?
Mok Oh is the Chief Scientist of PayPal. He is responsible for ensuring that PayPal makes effective use of data, exploring big data for predictive indications about future buying trends in its customers. He is also responsible for bringing PayPal users get the best possible experiences. According to Oh, the mission of the data scientist is to build a credible data model, then get more data about observed behavior to improve the model.

How to model the Commercial Brain?
PayPal is trying to model a person’s brain, at least the part of the brain that decides how to shop, when to shop, and what you want. PayPal is trying to reverse-engineer transactional data to figure out what people are going to buy next. Despite having petabytes f data, it is never enough since there are a lot of behaviors Paypal needs to model.

What important advice offered by Oh to data scientists?
Data scientists tend to focus on a very small piece of data without occasionally stepping back to take in the whole problem. The other pitfall is a tendency to over-focus on technology when business acuity is important. Organizations tend to employ the most technology-savvy person on the job, rather than the most business-savvy person. Oh says “knowing the right question, or problem to solve is very important”. It is because computer scientists are not trained to ask the right business questions.

What are key skills of the data scientist?
In the long run, the key skills of the data scientist, regardless of the amount of data he or she can collect or the type of tool he or she is master at, may be an intuitive sense of appropriate business questions as the analysis begins, and solid judgment when it reaches the end. Furthermore, the data scientist needs to look at each dataset on a case-by-case basis so as to understand the “signal strength” of data.