make sure the 2 apps have separate appNames in `pio app list` and have different indexNames in their engine.jsons.
1) appNames are where to get input, if the same then only params will be making different models, not different data. A PIO “app” is really a dataset. 2) indexNames tell the UR where to store the model in Elasticsearch, if 2 engin.jsons have the same indexName, the latest `pio train` will overwrite the previous one. On Apr 30, 2017, at 10:13 PM, Vaghawan Ojha <[email protected]> wrote: Hi, I'm using two seperate Universal recommender app in same machine. Everything is fine, but whenever I retrain one app, the score in the other app always goes to zero. However recommendation seems fine as far as I could see. Why this happens? I'm using different port to deploy the different apps. Have anyone else gone through the same problem? -- You received this message because you are subscribed to the Google Groups "actionml-user" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected] <mailto:[email protected]>. To post to this group, send email to [email protected] <mailto:[email protected]>. To view this discussion on the web visit https://groups.google.com/d/msgid/actionml-user/CA%2B69RXY0ncgUngGai5ztBwsqSwt%3DZTyUcj%2B0ccqhzi_bqS%3D01A%40mail.gmail.com <https://groups.google.com/d/msgid/actionml-user/CA%2B69RXY0ncgUngGai5ztBwsqSwt%3DZTyUcj%2B0ccqhzi_bqS%3D01A%40mail.gmail.com?utm_medium=email&utm_source=footer>. For more options, visit https://groups.google.com/d/optout <https://groups.google.com/d/optout>.
