Hi super user: Thanks for your response. I go to google and type SAS on Demand for Academics and it takes me to the site SAS OnDemand for Academics | SAS<> I get this at work and at home. I will try https://welcome.oda.sas.com/<> at home and see if makes any difference. But I doubt it. ... View more

Hi Jackie: Thanks very much for your feedback. You said "What happens when you try to login at home? Blank screen? Error message? A screen shot would be helpful. SAS OnDemand for Academics does have browser requirements. Perhaps your Edge browser has not been updated in a while. One thing you could try is installing the latest version of Firefox or Chrome browser, then see if one of those works." 1. When I logon from home I am told that the user id or password is incorrect. * This is the same user ID and password that I use at work and I get logged in no problem. [I just logged in this morning from work[ * I just got the computer and was provided with Microsoft Edge, which is the same as what I have at work. 2. I also logged on from work using Chrome and was able to log in with that as well. [just did this this morning] 3. I will try installing Chrome on my home computer and see if that works, but frankly I doubt it. Thanks Michael Quigley ... View more

Hi Rachel: Thanks very much for getting back to me so quickly. You asked: Oh no! To better troubleshoot, are you using the same browser type (Chrome or Firefox) in both locations? Also, do you use the same computer at work and at home? Lastly, do you use VPN at either location? My Response: 1. I use a different computer at home and at work. 2. I have the same browser [Microsoft Edge] at both. 3. My work computer probably does have VPN [Virtual Private Network], but I am not sure about my home computer. I have Microsoft 365 and use a modem. Any suggestions ? Thanks Michael Quigley Michael Regan Quigley Ph.D., Vice President - Financial Crimes Model Development Center of Excellence (CoE) 333 Market Street , San Francisco, Ca 94104 Tel: 510-282-0157 Cell: 510-282-0157 Michael.r.quigley@wellsfargo.com ... View more

Great Idea this worked. I tried a number of different results some examples are shown below:   First: One layer 2 neurons: proc hpneural data=tempq;    input &keep_it;    id perf_seq_num &target &validate &weight ;    target &target / level=nom;    hidden 2;   partition rolevar=&validate(train=0);    train outmodel=model_l1_n2 numtries=5 maxiter=1000;    scores out=scores_l1_n2;    code file = "&codefile";    weight &weight;   run;   Second: 2 Layers 3 Neurons:   proc hpneural data=tempq;    input &keep_it;    id perf_seq_num &target &validate &weight ;    target &target / level=nom;    hidden 3;    hidden 3;   partition rolevar=&validate(train=0);    train outmodel=model_&model numtries=5 maxiter=1000;    score out=scores_&model;    code file = "&codefile";    weight &weight;   run;   Third: 5 layers 3 Neurons:   proc hpneural data=tempq;    input &keep_it;    id perf_seq_num &target &validate &weight ;    target &target / level=nom;    hidden 3;    hidden 3;    hidden 3;    hidden 3;    hidden 3;   partition rolevar=&validate(train=0);    train outmodel=model_&model numtries=5 maxiter=1000;    score out=scores_&model;    code file = "&codefile";    weight &weight;             Fourth: 2 Layers First layer 100 neurons Second layer 50 neurons:   proc hpneural data=tempq;    input &keep_it;    id perf_seq_num &target &validate &weight ;    target &target / level=nom;    hidden 100;    hidden 50;   partition rolevar=&validate(train=0);    train outmodel=model_&model numtries=5 maxiter=1000;    score out=scores_&model;    code file = "&codefile";    weight &weight;   run;     ... View more

There are 89,000 observations and 74 variables. So I am surprised to it is not working ... View more