09-01-2015
matovua
Calcite | Level 5
Member since
10-11-2012
- 16 Posts
- 0 Likes Given
- 0 Solutions
- 0 Likes Received
-
Latest posts by matovua
Subject Views Posted 3149 06-18-2013 04:33 AM 3375 06-18-2013 04:16 AM 3307 01-18-2013 07:06 AM 966 11-12-2012 09:10 AM 983 10-12-2012 02:02 AM 1105 10-11-2012 03:00 PM -
Activity Feed for matovua
- Posted Re: reading an oracle database directly from sas on SAS Programming. 06-18-2013 04:33 AM
- Posted reading an oracle database directly from sas on SAS Programming. 06-18-2013 04:16 AM
- Posted Help with over/under sampling of the rare event in predictive modelling on SAS Data Science. 01-18-2013 07:06 AM
- Posted I would want access to a good tutorial for clustering using sas enterprise miner on SAS Data Science. 11-12-2012 09:10 AM
- Posted Re: none of the churn predicted customers have not churned four months leter. on SAS Data Science. 10-12-2012 02:02 AM
- Posted none of the churn predicted customers have not churned four months leter. on SAS Data Science. 10-11-2012 03:00 PM
06-18-2013
04:33 AM
Thank you LinusH, The Database guys here tell me that by the time i am able to access the oracle database through sqldeveloper and vb.net i have SQL*NET installed already. Is there a way i can test if it is installed, i have downloaded a "intallclient-sqlplus-nt-11.2.0.30". When i run it to intall sql plus it asks me for user name and password and i dont know waht to put. the database guys tell me i dont need to install anything Anthony
... View more
06-18-2013
04:16 AM
I have the following information i use to connect to an oracle database, it is succssful through sqldeveloper and vb.net, However, it fails with SAS. The SAS Statement is also below mat1 = (DESCRIPTION = (ADDRESS_LIST = (ADDRESS = (PROTOCOL = TCP)(HOST = mid2-scan)(PORT = 1539)) ) (CONNECT_DATA = (SERVICE_NAME=mat1)) ) username password SAS libname i use is libname oralib oracle user="username" password="password" path="mat1" schema="mat1"; The error message i get is "the oracle engine cannot be found" "error in the libname statement" I have been access the oracle database through "sqldeveloper", i have SAS/ACCESS installed I don't know what to next, i have tried google but not good way through Do i have to do anything with the port, and host Anthony
... View more
01-18-2013
07:06 AM
Dear All I have done a model which perfoms well when i oversample the rare event at 25% but gives too many False Positives. When i remove over sampling the missclassfication rate is good but the actual predicted and have actually churned number is too small to be used. I need your help on what can do I am using SAS enterprise Miner , Thanks
... View more
11-12-2012
09:10 AM
Dear Members, I am starting to use clustering of customers using SAS enterprise miner, unfortunately I am failing to get access to a good reading material for this purpose. Thank you very much Anthony
... View more
10-12-2012
02:02 AM
Thank you Reeza, Below is what i went through to construct the model. getting the churn variable 1. I got all active subscribers for may 2012. Checked all that are still present in August = Non-churn and those not present are the churn. 2. Using the churn variable for may I constructed the churn prediction variables using data for the months of Mar,April, and May. With these I got usage statistics per susbsciber for each month, constructed means, ratios and I ended up with about 500 variables. the data used included revenues for voice, sms, data, value added services etc broken into on-same-network, other-networks, international. 3. I subjected the constructed data to the model development process with SAS enterprise miner. The model had the following nodes a. sample node: with rare event oversampled to 25% from 4.9% using stratified sampling (total sample is about one million subscribers). b.data partition = training 50%, varidation 30% and testing 20% c.Principle components and variable transformation using the distribution. d.Decision tree, nueral network and regression models from the above nodes. one decision tree from the partitioned data. The Decision tree from the variable transformation perfomed best with missclassfication rate = 0.18 I scored the model and applied results to data for June. The results are presented in the file attached. Thank you again for you help
... View more
10-11-2012
03:00 PM
I am relatively new to predictive modelling, I have predicated churn for a telcom customers. I developed the model for May 2012 and submitted the scores to the same data. I had about 9% customers predicted as high potential churners. I was disappointed that all the predicted churners are still present even up to now. I subjected the data to churn scorres that were developed by an expert who visted my office and the results were the same. the missclassification rate 18%. Thank you for your help. Where can i improve to have a better churm model.
... View more