Uncategorized
Guest Post: Can Database Developers do Data Mining ?
I was recently invited by Sandro Saitta, who runs the Data Mining Research blog (http://www.dataminingblog.com/), to write a guest blog post for him. The topic for this guest post was Can Database Developers do Data Mining ?
The original post is available at Guest Post- Can Database Developers do Data Mining –
Here is the main body of the post
Over the past 20 to 30 years Data Mining has been dominated by people with a background in Statistics. This is primarily due to the type of techniques employed in the various data mining tools. The purpose of this post is to highlight the possibility that database developers might be a more suitable type of person to have on a data mining project than someone with a statistics type background.
Lets take a look at the CRISP-DM lifecycle for data mining (Figure 1). Most people involved in data mining will be familiar with this life cycle.
Figure 1 – CRoss Industry Standard Process for Data Mining.
It is will documented that the first three steps in CRISP-DM can take up to 70% to 80% of the total project time. Why does it take so much time. Well the data miner has to start learning about the business in question, explore the data that exists, re-explore the business rules and understand etc. Then can they start the data preparation step.
Database developers within the organisation will have gathered a considerable amount of the required information because they would have been involved in developing the business applications. So a large saving in time can be achieved here as this will already have most of the business and data understanding. They are well equipped at querying the data, getting to the required data quicker. The database developers are also best equipped to perform the data preparation step.
If we skip onto the deployment step. Again the database developers will be required to implement/deploy the selected data mining model in the production environment.
The two remaining steps, Modelling and Evaluation, are perhaps the two steps that database developers are less suited too. But with a bit of training on Data Mining techniques and how to evaluate data mining models, they would be well able to complete the full data mining lifecycle.
If we take the stages of CRISP-DM that a database developer is best suited to, Business Understanding, Data Understanding, Data Preparation and Deployment, this would equate to approximately 80% to 85% of the total project. With a little bit of training and up skilling, database developers are the based kind of person to perform data mining within their organisation.
Job: ETL/Data Warehouse Consultant
Distinct Partners are a new opening for a ETL/Data Warehouse Consultant.
Following a period of growth, we are now looking for experienced ETL professionals to join our consultancy team. If you are looking for a challenge in management consultancy and believe that you have the qualities to succeed in a dynamic and high growth consultancy environment, then we would love to hear from you.
Expertise Required:
- Data Integration skills (at least one of the following)
- Proprietary: Informatica, SAS Data Integration Studio, IBM Data Stage, Oracle.
- Open Source: Talend, Postgres, My SQL, CUDA, Python.
- Strong querying , data analysis and data flow mapping skills (must)
- Data quality skills – checks, standardisation, house holding etc (understanding)
- Data architecture skills (understanding)
- data modelling (normalisation, referential integrity etc)
- dimension modelling (dimensions, facts, SCDs etc
- XML scripting and open source data integration skills (strong plus)
- Database/ETL performance tuning and programming skills
Full details can be found at
http://www.linkedin.com/jobs?viewJob=&jobId=1556819&svfId=822045&goback=%2Emid_I2774654840*42
If you would like to apply for the job you can email your CV to
Gina Cassidy gina.cassidy@distinctpartners.com
and mention you heard about the job from me
My Blog & others
Over the past few years I have been contributing on Data Mining and Oracle Data Miner topics on the BI-Quotient blog
http://www.business-intelligence-quotient.com/
Over the past few months I have decided to expand my blog postings to include all the things I’m currently doing or things that I find interesting. The main theme will be ‘Data is King’
The new blog will include posts on the following topics:
- Oracle
- Oracle Data Miner
- Data Mining
- Data Management
- My research
- Database Design
- and generally anything else that I find interesting and relating to Data.
This is where this blog come into its own. This will be my main blog going forward. It will contain all my posts, including a copy of these that I post on the BI-Quotient blog
Deputy Editor for Oracle Scene (June edition)
Today I got a phone call from Jennifer from the UKOUG office asking me would I be interested in helping out with some (minor) editing of 4 articles for the June edition of Oracle Scene.
I will also have an article in this edition of Oracle Scene (a 5 page spread).
I’ve had a quick look through the 4 articles and they are an interesting bunch of articles.
Oracle Scene will be holding elections over the coming months for a more longer term deputy editor. This will go out to the user community for a public vote. I might put might name forward for this.
VirtaThon–Online Confernce July
Yesterday I received an email telling me that my presentation submission for VirtaThon (Virtual Conference for the Oracle, Java & MySQL Communities).
The presentation is titled, Getting Started with Oracle Data Miner 11G R2.
I would really like to give an online demo of the tools or even to be able to show a view of the demo, but it looks like I may have to do it with good old Powerpoint.
Oracle Data Miner 11g R2 – New Features
There are many new features in the new tool and these can be grouped under the following headings:
- Data Exploration
: The first step of every data mining project involves investigating the data to try to learn from the data, gather some initial information and investigate if there are any patterns in the data
- Workflow interface
: This gives the user a more intuitive way to work with the tool and with the overall process of data mining. It allows for the repeated rerunning of the data modelling process without having to input and define each step again. You had to do this in the previous version of the tool
- Generate multiple models at the same time
: This is one of the major improvements in the tool. It allows you to create models using each of the algorithms available for each data mining techniques, in one step, instead of repeatedly defining each in the pervious version of the tool.
- Graphical representations of models
: Another major new feature. The tool now produces Decision Trees and Clusters graphically. With the Decisions Trees we can now see on the screen how the tree looks and then to investigate the different branches of it to see how the tree was built. We can also see what rules were generated to create these branches.
Evaluation of all the developed models
: Another major new feature. In the previous version of the tool you were presented with a set of evaluation diagrams and measures for each model. You were not able to see all the results on one graph and you had to resort to having multiple windows open at the same time to try to compare the results. Now we can get the evaluation measures and graphs for all the models on the one set of graphs. This allows a data miner to concentrate on determining the most appropriate model to use.
Each of these new features really deserve a post by themselves to illustrate their new capabilities. These posts will follow over the coming weeks.
Brendan
2010 Rexer Analytics Data Mining Survey
The Rexer Analytics 4th Annual Rexer Analytics Data Miner Survey for 2010 is now available. 735 data miners participated in the 2010 survey. The main highlights of the survey are:
• FIELDS & GOALS: Data miners work in a diverse set of fields. CRM / Marketing has been the #1 field in each of the past four years. Fittingly, “improving the understanding of customers”, “retaining customers” and other CRM goals are also the goals identified by the most data miners surveyed.
• ALGORITHMS: Decision trees, regression, and cluster analysis continue to form a triad of core algorithms for most data miners. However, a wide variety of algorithms are being used. This year, for the first time, the survey asked about Ensemble Models, and 22% of data miners report using them.
A third of data miners currently use text mining and another third plan to in the future.
• MODELS: About one-third of data miners typically build final models with 10 or fewer variables, while about 28% generally construct models with more than 45 variables.
• TOOLS: After a steady rise across the past few years, the open source data mining software R overtook other tools to become the tool used by more data miners (43%) than any other. STATISTICA, which has also been climbing in the rankings, is selected as the primary data mining tool by the most data miners (18%). Data miners report using an average of 4.6 software tools overall. STATISTICA, IBM SPSS Modeler, and R received the strongest satisfaction ratings in both 2010 and 2009.
• TECHNOLOGY: Data Mining most often occurs on a desktop or laptop computer, and frequently the data is stored locally. Model scoring typically happens using the same software used to develop models. STATISTICA users are more likely than other tool users to deploy models using PMML.
• CHALLENGES: As in previous years, dirty data, explaining data mining to others, and difficult access to data are the top challenges data miners face. This year data miners also shared best practices for overcoming these challenges.
• FUTURE: Data miners are optimistic about continued growth in the number of projects they will be conducting, and growth in data mining adoption is the number one “future trend” identified. There is room to improve: only 13% of data miners rate their company’s analytic capabilities as “excellent” and only 8% rate their data quality as “very strong”.
You can request a copy of the full report by going to their data mining survey webpage
Changing the Domain of Oracle Database Server
I recently had the task of moving our Database server onto a new domain. The following steps outline what was involved in performing this task.
1. Change the Domain of the server
- Take the server of the current domain
- Reboot
- Change the domain to the new one
- Reboot
2. Update the Listener.ora and Tnsnames.ora
- Change to the new domain name
3. Make sure the the instance is running
- sqlplus / as sysdba
4. Drop the Enterprise Manager Console
- emca -deconfig dbcontrol db -repos drop
- Enter the SID name (ORA11gDB)
- Listener port number = 1521
- Password for SYS user
- Password for SYSMAN user
- Do you wish to continue = Y
- Depending on the size of the DB it can take some minutes to complete the (10 minutes)
5. Reinstall the Enterprise Manager Console
- emca -config dbcontrol db -repos create
- Enter the SID name (ORA11gDB)
- Listener port number = 1521
- Password for SYS
- Password for DBSNMP
- Password for SYSMAN
- Email address for notification
- Outgoing mail (SMTP)
- Do you wish to continue = Y
- Again this can take some minutes to complete (20 minutes
6. Restart the database
7. Test connections
8. All should be OK
New Oracle Data Miner tool is now Available
Today the new Oracle Data Miner tool has been made available as part of the SQL Developer 3.0 (Early Adoptor Release 4).
The new ODM tool has been significantly redeveloped, with a new workflow interface and new graphical outputs. These include graphical representations of the decision trees and clustering.
To download the tool and to read the release documentation go to
http://tinyurl.com/62u3m4y
If you download and use the new tool, let me know what you think of it.
Data Analytics Videos–CNBC–Big Brother–Big Business
The following list of videos are available on Youtube from the CNBC program Big Brother – Big Business. Each video is between 8 minutes and 10 minutes long.
They give a good incite into how data analytics can be used and is currently being used by organisations to gain new information and knowledge of what is going on in their business.
Most of the techniques used in the examples given in the videos do not use any complex technique, but shows how a business can use their data to gain a incite into what is really going on in business
Video1, Video2, Video3, Video4, Video5, Video6, Video7, Video8, Video9, Video10
Let me know what you think of these videos.
If you come across any other interesting Data Analysis videos, let me know and I can add them to the list above
Brendan Tierney
New Oracle Data Mining tool video
Charlie Berger has recently put together a video demonstrating the new Oracle Data Mining tool.
The link to this video is
http://tinyurl.com/6jhsth4
The video gives a demonstration of some of the main stets in building and applying a classification model. He also demonstrates applying classification to the same data.
The new ODM interface is due to me made available within the next month or two on a limited basis initially and will be part of an Early Adopter (EA) release of SQL Developer 3.
Brendan
- ← Previous
- 1
- …
- 9
- 10
- 11
- Next →
Ora-lytics 
You must be logged in to post a comment.