|
Data Mining - Sales company exampleNow that you know a little bit more about data mining (and if you don't, you can here), let's look at a quick 'actual' example using a real company. I had a contact with a small sales company and remember having a conversation with my contact about bringing in more business for her company. This company actually coached life skills, so they would have weekly classes where students would come in and learn about a variety of different lifeskills. For example, they had an improvisational class geared twords people in the sales industry. A good sales person has to be quick on their feet and be able to read and adapt to a customer, so this was a very beneficial sales class. They also offered a variety of other classes, including a class that gave shy children self confidence. After speaking with my contact at this company, I realized they kept all different types of data on how they signed someone up for a class, but had no way to practically sort this data. So I suggested data mining, and told her it could not only increase her sales, but also decrease her company wide expenses. She was of course skeptical, but now is fully on board and uses data mining at her company and would never have it another way. For this example, I'll quickly explain their sales process so you have an idea of how to follow along with the rest of the introduction. They had 2 different class types (improv and life skills) and three different markets (children (4-12), teens (13-17) and adults (18 +). They got their leads (potential sales) from the following avenues: school fairs, trade shows and website. When I finally got in and looked at all the data, they had tons of it. But unfortunately it was scattered about and missing information left and right. Now we could have taken the quick road, and 'estimated' the missing data and filled them in with numbers we thought would work. This of course is not good. The more complete your data set is, the better results you will get. So what we did was we decided that for 2 months, her business operation would continue as normal, however, all important data would be recorded accurately. Once we had this 2 month data set, we ran it through a software program and group data together to see what came out. Whenever a sales person made a potential customer contact, they were told to record the following information; (note: we recorded much more data than this, but since this is meant to be an introductory walk thu of data mining, I have edited it down to the following four data sets. If you would like more infomation on the full project, just send me an email at Matt@Launsby.com)
We had one data sheet like this for every time a sales person went to a school or tradeshow, or logged into email and took names from the website:
Once we had recorded this data for 2 months, we were able to go through it all and sort it. This is the basics of data mining. Recording data and sifting through it to find correlations you didn't think existed or wouldn't have found had you not data mined. Simple graphs and scatter plots can be good starting points for data mining. Frequently you will need to go beyond these approaches and use powerful tools such as CART, Neural networks, or association techniques. As I said earlier, this walk through contains just a small amount of the data we went through, however with the actual data we found very interesting correlations that we never would have found without mining this data. Some of the ones we found that helped the company immensely were;
That is the basics of Data Mining. This is still a fairly new area of quality control but most companies already have been storing the data they need to make this a succesfull endeavor for them. And the ones that haven't, now is a perfect time to start. Launsby Consulting has been teaching data mining techniqes since 1991. To learn more about how we can help your company become more competitive, feel free to email me personally at Matt@Launsby.com, or give us a call at 1-800-788-4DOE (1-800-788-4363) or 719-282-1143. I hope you have found this example informative, and feel free to pass it on to anyone you like. However, if you are going to show this in a class or conference, please credit Launsby Consulting. Thank you for your time, and I look forward to hearing from you. We also have an always growing dictionary of quality control terms and walk through's. We have the following data mining terms currently, and are always adding more;
Launsby Consulting offers a variety of tools on data mining. Launsby Consulting has been an industry leader in teaching designed experiments since 1991. To view our partial client list, just click here.
|
||||||
