# Model Reader **URL:** \ **Category:** KNIME Analytics Platform\ **Created:** [July 3, 2022, 1:45am UTC](https://forum.knime.com/t/model-reader/44722 "2022-07-03T01:45:17Z")\ **Posts on this page:** 8\ **Page:** 1
**Author:** ![rfeigel](https://forum-cdn.knime.com/letter_avatar_proxy/v4/letter/r/7ea924/32.png) [@rfeigel](https://forum.knime.com/u/rfeigel)\ **Post date:** [July 3, 2022, 1:45am UTC](https://forum.knime.com/t/model-reader/44722/1 "2022-07-03T01:45:17Z")
Does someone have a simple example workflow using the Model Reader node and a new dataset? Thanks. ---
**Author:** ![mlauber71](https://forum-cdn.knime.com/user_avatar/forum.knime.com/mlauber71/32/73590_2.png) [@mlauber71](https://forum.knime.com/u/mlauber71)\ **Post date:** [July 3, 2022, 5:58am UTC](https://forum.knime.com/t/model-reader/44722/2 "2022-07-03T05:58:12Z")
@rfeigel how about this one ![image](https://forum-cdn.knime.com/uploads/default/original/3X/3/5/35e210c8b8023280888505f09106030ae55b9690.jpeg) > **[Fraud Detection: Model Deployment – Maarit](https://hub.knime.com/knime/spaces/Examples/latest/50_Applications/39_Fraud_Detection/02_Fraud_Detection_Deployment~FPT9HWoLh1QaGaic)** > > This workflow, the deployment workflow, reads the trained model, as well as the new transaction and applies the model to classify it. Like in the training work… ---
**Author:** ![rfeigel](https://forum-cdn.knime.com/letter_avatar_proxy/v4/letter/r/7ea924/32.png) [@rfeigel](https://forum.knime.com/u/rfeigel)\ **Post date:** [July 4, 2022, 1:03am UTC](https://forum.knime.com/t/model-reader/44722/3 "2022-07-04T01:03:50Z")
Thank you. That was very helpful. A related question - the new data table with unclassified data still must have a “class” column with the classification arbitrarily set to one of the possible classifications. I assume this is necesaary to work with the new predictor node. ---
**Author:** ![rfeigel](https://forum-cdn.knime.com/letter_avatar_proxy/v4/letter/r/7ea924/32.png) [@rfeigel](https://forum.knime.com/u/rfeigel)\ **Post date:** [July 4, 2022, 1:47am UTC](https://forum.knime.com/t/model-reader/44722/4 "2022-07-04T01:47:14Z")
I tested the assumption in my last message and its seems to work correctly. If I’m missing something, please let me know. ---
**Author:** ![mlauber71](https://forum-cdn.knime.com/user_avatar/forum.knime.com/mlauber71/32/73590_2.png) [@mlauber71](https://forum.knime.com/u/mlauber71)\ **Post date:** [July 4, 2022, 6:17am UTC](https://forum.knime.com/t/model-reader/44722/5 "2022-07-04T06:17:58Z")
@rfeigel typically it should not require such a column since this is what the model is supposed to predict ---
**Author:** ![rfeigel](https://forum-cdn.knime.com/letter_avatar_proxy/v4/letter/r/7ea924/32.png) [@rfeigel](https://forum.knime.com/u/rfeigel)\ **Post date:** [July 4, 2022, 4:01pm UTC](https://forum.knime.com/t/model-reader/44722/6 "2022-07-04T16:01:11Z")
Thnaks. I’ll try without. ---
**Author:** ![rfeigel](https://forum-cdn.knime.com/letter_avatar_proxy/v4/letter/r/7ea924/32.png) [@rfeigel](https://forum.knime.com/u/rfeigel)\ **Post date:** [July 4, 2022, 11:09pm UTC](https://forum.knime.com/t/model-reader/44722/7 "2022-07-04T23:09:08Z")
Your absolutely correct. I removed the classification column from the new data set and it worked perfectly with the model reader. Thanks very much for your help. ---
**Author:** ![system](https://forum-cdn.knime.com/uploads/default/original/1X/ab3ccf34482a0329361734a18199390177204f15.png) [@system](https://forum.knime.com/u/system)\ **Post date:** [October 2, 2022, 11:09pm UTC](https://forum.knime.com/t/model-reader/44722/8 "2022-10-02T23:09:56Z")
This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.