1
$\begingroup$

I am very new to machine learning. I just went through some of the tutorials in Azure and completed one practice workflow(car price prediction). I hope I can ask basic questions here.

Scenario : We get service request from our customers via email. This has fields like customer name, user name, email id, Equipment affected, type of call and Issue experienced(this is a free text area).

The employee reads this email, mainly the issue experienced. Based on the issue experienced section, s/he takes the appropriate actions. We will have 4-6 fields(type of request , a few questionnaire etc). The issue experienced is a free text area where customer can write anything about the issue.

Does this qualify as a AI model if we have last 2-3 years data. If yes, Is multi class classification the solution? If not, which ML algorithm needs to be used here. Can I rely on Azure for this or do we need to build a new model/algorithm for this?

Sorry if it is a too basic question

$\endgroup$
  • $\begingroup$ What does employee do after this, does he/she classify the request in some categories ? "The employee reads this email, mainly the issue experienced. Based on the issue experienced section. " $\endgroup$ – Shamit Verma Mar 11 at 10:18
  • $\begingroup$ He reads this and in another application he logs a call. There he has to fill the request type and a number of questionnaires. This is mainly based on the 'issue experienced' field. Here customer can write free text $\endgroup$ – rahul raj Mar 11 at 10:53
0
$\begingroup$

He reads this and in another application he logs a call. There he has to fill the request type and a number of questionnaires.

This is a "multi class" classification problem.

You can start with a library that makes it easy to mix text , categorical and numerical attributes.

Text : "issue experienced" attribute (Library should be able to apply NLP on text ) Categorical : "type of request" and similar attributes Numerical : "price" and similar attribute (if applicable)

One such library is : Uber Lugwig

If you have data in CSV, it should not take more than a few hours to train the model.

Documentation : https://uber.github.io/ludwig/user_guide/

Introduction : https://hackaday.com/2019/02/25/ludwig-promises-easy-machine-learning-from-uber/

$\endgroup$
  • $\begingroup$ Thank you so much for the reply. Not able to access second link. It says The webpage at hackaday.com/2019/02/25/… might be temporarily down or it may have moved permanently to a new web address. $\endgroup$ – rahul raj Mar 11 at 11:15

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.