The Fifth Elephant 2019

Gathering of 1000+ practitioners from the data ecosystem

Tickets

Price Recommendations - Driving Revenue Strategy Using Machine Learning

Submitted by Shikhar Gupta (@shikhargupta) on Thursday, 13 June 2019


Preview video

Session type: Full talk of 40 mins

Abstract

Brief Description:
Pricing in hotels can result in a lot of optimisation given that there is limited inventory to sell each day. This session focuses on how Treebo developed an automated machine learning based pricing engine within 2 months and scaled it up in next 6 months to recommend real-time prices for 400 hotels. This resulted in ~26% improvement in booked revenue, 30 days in advance.

Abstract:

If you want to run a profitable hotel chain, price is what you can play the most with to optimise revenue and profits.
Treebo hotels is a technology powered hotels startup that ties up with hotel partners with a value proposition of higher revenue for them and a better quality for the guests. They wanted to develop a system which could optimise revenue for every hotel by recommending optimal prices. A system that could automatically keep changing prices throughout the day, based on multiple factors like competitor prices, seasonality, web traffic, time remaining to sell, etc.

Pricing for hotels is more complex than pricing for a regular item like a shoe because it involves a booking date and a stay date. So on a particular day, you can set different prices for different future stay dates. Doing this manually is sub-optimal and prone to errors. So, you would need a system that can make changes multiple times a day for multiple future dates.

While existing products can be helpful in kickstarting an automated pricing system, they would come with some constraints. This session will throw light on the pros and cons of building your own system rather than subscribing to a third party product.

Shikhar will talk about how they came up with a minimum viable product in just two months and scaled it up to complete pricing for 400 hotels within the next 6 months. This helped the company in booking 26% more revenue, at least 30 days in advance which is wonderful for the business. They’ll also cover the challenges faced like sourcing of market data, building data pipelines and convincing business teams to rely heavily on their solution and how they dealt with them.

Intended audience: Product managers, Data scientists, Revenue Managers, Business leaders

Key takeaways: How to set up your own pricing engine, how to quickly scale-up a data science project for the benefit of business

Outline

Brief understanding about the business
Previous state and desired state
What did we build?
The journey of building the new system
Challenges faced while building and how we tackled them
Success Metrics and Impact

Speaker bio

Shikhar is Product Manager for Pricing at Treebo hotels. In last 3 years at Treebo, he has played multiple roles including business and operations.
Previous to that, he was part of Flipkart. There, he was part of the monetisation business and played key role in scaling up that business. He was part of the team that launched a completely automated new product called Product Listing Ads.
Before that, he was an analyst at Mu Sigma, a major player in providing analytical services to fortune 500 clients. He worked on a couple of projects there involving logistic regression modelling and customer loyalty analytics.

Slides

https://docs.google.com/presentation/d/1tW0AGPcVwNHKJcDnGDtEVPp82MUMtQF5fKTGGMT9FMA/edit?usp=sharing

Preview video

https://www.youtube.com/watch?v=LExgRgVj_Yc&t=6s

Comments

  • Abhishek Balaji (@booleanbalaji) Reviewer 5 months ago

    Hi Shikhar,

    Thank you for submitting a proposal. We need to see more detailed slides to evaluate your proposal. Your slides must cover the following:

    • Problem statement/context, which the audience can relate to and understand. The problem statement has to be a problem (based on this context) that can be generalized for all.
    • What were the tools/frameworks available in the market to solve this problem? How did you evaluate these, and what metrics did you use for the evaluation? Why did you pick the option that you did?
    • Explain how the situation was before the solution you picked/built and how it changed after implementing the solution you picked and built? Show before-after scenario comparisons & metrics.
    • What compromises/trade-offs did you have to make in this process?
    • What is the one takeaway that you want participants to go back with at the end of this talk? What is it that participants should learn/be cautious about when solving similar problems?

    We need your updated slides and preview video by Jun 27, 2019 to evaluate your proposal. If we do not receive an update, we’d be moving your proposal for evaluation under a future event.

Login with Twitter or Google to leave a comment