The Fifth Elephant 2019

Gathering of 1000+ practitioners from the data ecosystem

Tickets

Text Classification, Interpretability, and Summarisation at Scale

Submitted by Siddhant Panda (@siddhantpanda) on Tuesday, 16 April 2019

Session type: Short talk of 20 mins

Abstract

The Freshdesk product is used by over 150,000 customers for resolving customer support tickets. Each customer configures workflows within the product that are specific to their approach to ticket resolution. Traditionally, these use a hand-tuned rule-based system that serves well when a support organisation is relatively small. However, as businesses scale and customer needs become more complex, rule-based systems are unable to keep up, resulting in increases in issue resolution times and a drop in customer satisfaction.
In order to enable our customers to meet increasing customer expectations and reduce unnecessary manual effort, we have designed an NLP system that:
1. Automatically routes & prioritises tickets to the right support agent using historical data
2. Reduces dependence on a rule-based system
3. Helps agents and administrators understand why a particular prediction was made

Outline

  1. An overview of ticketing systems and rule-based routing
  2. Various approaches we looked at to solve routing and prioritisation
  3. Scaling the data science pipeline to 70,000+ models
  4. Building interpretability models to help users understand the reason for predictions
  5. Future Directions - we would like to take this further for text summarization where we would shorten the document that would provide a brief overview of it.

Speaker bio

Data scientist at Freshworks

Comments

  • Anwesha Sarkar (@anweshaalt) Reviewer 4 months ago

    Thank you for your submission. Submit your preview video and slides by 23rd March(latest). It helps us to provide a fair evaluation to the proposal and close the review process.

  • Zainab Bawa (@zainabbawa) Reviewer 3 months ago

    Siddhant, we haven’t received your draft slides and preview video. Without these two details, we cannot evaluate your proposal. If we don’t receive this by 10 May, we will be compelled to move your proposal to reject. You are welcome to resubmit the proposal thereafter, with slides and preview video.

  • Zainab Bawa (@zainabbawa) Reviewer 3 months ago

    The following comments came from the initial review:

    1. What is the problem that you are trying to solve? How can this problem be extrapolated for participants who do not have the Freshworks’ use case?
    2. What was the approach chosen to solve the problem?
    3. Why did you choose this approach?
    4. Which other approaches did you consider and evaluate when solving the problem? What were the comparison metrics? Why did you finalize this approach over others?
    5. Deep dive into the solution?
    6. What has been the journey thus far, including before-after scenarios?
    7. What is the takeaway for the audience from this journey?

    When you submit slides, the above points have to be added along with data points to substantiate claims.

Login with Twitter or Google to leave a comment