Tell me more ×
Cross Validated is a question and answer site for statisticians, data analysts, data miners and data visualization experts. It's 100% free, no registration required.
up vote -3 down vote favorite

I want some guidance for my final year project which is on data mining. I am hoping to develop a system which will show the right person for the right job using historical data of the employees such as language expertise, experience in IT industry, skills etc. Where should I start?

I want some guidance in using the data mining API alone with Java and MySQL. I have the problem in implementation. I have decided to use decision tree algorithm (C4.5). Are there any recommended algorithms?

Thank you

share|improve this question
Have you ever taken a course on data mining? What do you know about it? What ideas do you have to go about your project so far? Did you discuss the same with your supervisor? – Arun Feb 24 '12 at 18:35
2  
-1. If you are just setting out with the general problem you set out in your first question, I think it is too early to start thinking about which algorithm to use. – Peter Ellis Feb 25 '12 at 0:10
1  
-1. I would not recommend basing promotion decisions on data mining results. I've been involved in enough job interviews to know that some people who look fantastic on paper (what you would put into your model) are not the right fit for a job. – Michelle Feb 25 '12 at 3:40
@Michelle This is just a statistical exercise, it's not actually being implemented. However, if a company did have such a system, I could see being a useful tool (one of many factors to base promotions on). – Glen Feb 25 '12 at 17:38
This question is not fit in site's standards, which require that the questions should be able to get a single, definite answer. Please earn some reputation and then use chat for this kind of vague discussions or use some data miners' forum or discussion board rather than this site. – mbq♦ Mar 2 '12 at 16:32

closed as not a real question by mbq♦ Mar 2 '12 at 16:26

It's difficult to tell what is being asked here. This question is ambiguous, vague, incomplete, overly broad, or rhetorical and cannot be reasonably answered in its current form. For help clarifying this question so that it can be reopened, see the FAQ.

2 Answers

up vote 0 down vote

That's pretty vague. If you want better answers, give some more info about your background and what's giving you trouble. Is it finding the data? Is it picking the right algorithm(s) or the implementation? Is it learning data mining from scratch? If it's the latter, take a look at Data Mining: Practical Machine Learning Tools and Techniques. That's a pretty good intro to DM using Weka.

share|improve this answer
+1 for weka, it is a good way of getting some practical experience without spending too much time coding (coding the algorithms for yourself is also a useful activity, but leave it until later). – Dikran Marsupial Feb 24 '12 at 17:50
1  
(-1) for not making this a comment and using the shopping-cart approach – steffen Feb 24 '12 at 18:28
What is a shopping-cart approach? I am not familiar with this term. – Dimitriy V. Masterov Feb 24 '12 at 19:58
@DimitriyV.Masterov shopping-cart-approach refers to answers of the kind "if you mean that then I recommed this". It is generally recommended to discuss open/unclear parts with the OP in the comments first before posting an answer. That way this site can keep it's high quality and does not degrade into a "standard" forum. No offense ! – steffen Feb 25 '12 at 6:30
up vote 0 down vote

You can take a look at the Wikipedia article on data mining for free. It will give you a general overview on methods used in connection with data mining tasks.

From your task description one may suggest that you should have a look at classification algorithms.

share|improve this answer

Not the answer you're looking for? Browse other questions tagged or ask your own question.