Airline Travel industry is one of the biggest industries in the world worth 800 billion USD in annual revenues for commercial airlines alone. The industry generates approximately 2.5 quintillion bytes of information every day that remains unutilized. (Source IATA). There are multiple challenges that affect the airline industry. These challenges can be environmental (weather conditions, virus outbreaks like corona), geopolitical war, riots, terrorism), or economic (fuel price, currency fluctuations, recessions). In a very operationally complex environment like airline operations, these challenges seem more overwhelming Increasingly, customers are also expecting a highly personalized experience throughout their travel journey. To overcome these challenges and create a sustainable and profitable industry, the airline industry is seeking to harvest the power of data. IBS is constantly innovating and driving initiatives to solve some of these airline travel industry challenges using data. Here is an opportunity for the student community to be part of such an initiative and create innovative solutions using untapped industry data. Welcome to IBS Datathon !!!


There are two challenges in the Datathon. Students are free to choose any one challenge.

  1. Sentiment Analytics in Travel
  2. With the data set provided , develop a social media sentiment analytics solution to mine social media engagement data of passengers, to track and rate passenger sentiment while traveling.
    More and More Passengers express their feelings and opinions through social media networks. Analysis on this data could provide better insights towards making travel more personalized and consequently improve customer satisfaction.
    Explore the chances to find out the route wise sentiment through social media as a tool for

    • Improving the passenger experience for Airports and Airlines
    • Correlating and providing insights and solutions towards complaints / unruly passengers
    • Correlating with Ancillary Sales

    Twitter data containing relevant hash tags ( Provided in the Google Drive )
    Airport and Airline Timelines ( Provided in the Google Drive )
    (Data Source : IATA )
    Students are free to use any additional data set they consider relevant for solving this challenge.

  3. Disruption Management
  4. With the data set provided, create a solution to prevent and mitigate disruptions, taking into account various external data sources for potential correlations.
    *Disruption in Airline : “Disruption” is defined as “situations where a scheduled flight is cancelled, long or very long delayed, within 48 hours of the original scheduled departure time.
    Disruptions have a significant negative impact on airlines, airports and customer experience . Predicting and managing disruptions effectively will be a key aspect in improving the operational efficiency of airlines and airports.
    Develop an analytic solution for predicting disruptions allowing timely anticipation.
    10 days departure , Arrival and METAR** ( Provided in the Google Drive )
    Twitter data containing relevant hash tags ( Provided in the Google Drive ,also part of the challenge 1 )
    Airport and Airline Timelines ( Provided in the Google Drive ,also part of the challenge 1 )
    (Data Source : IATA )
    Students are free to use any additional data set they consider relevant for solving this challenge.
    (Hint - Coronavirus propagation dataset)
    ** METAR is a format for reporting weather information

    Evaluation Criteria
    Accuracy of the algorithm
    Data analytics and visualization quality
    Completeness of the solution and Final Presentation


  • What is the structure of the event?
  • The Datathon is structured as an online event with final presentation happening at CET on the tech fest date. The duration of the Datathon challenge is scheduled for two weeks, when each team will have access to the datasets provided. An evaluation will be held to qualify the top submissions and the results will be announced on 28th March. The selected teams will be invited to demo their solutions in front of a panel at the IBS booth on the 29th Mar. Please refer the “Agenda” for complete details.

  • Is this event conducted at CET on tech fest dates or is online solution submission sufficient? Also how to submit the solution online?
  • The solution should be submitted online using github, but the final presentation for the top participants (based on a pre evaluation) will be happening at CET on 28th March 2019.

  • How much time is available since unveiling the problem till solution submission?
  • IBS will provide the data and requirements on 12th and then the registered students will get time till 27th 3:00 PM to submit the solutions. Short listed solutions will be called out for a final presentation on 28th evening and the winners will be announced on 29th Evening.

  • Is it possible to change the event rule so that loners can participate?
  • No. The Datathon requires at least 3 members in the team for qualifying . This is to ensure the proper evaluation and judgment of the solutions.

  • Will there be any filtration from registered students?
  • All the registered students can participate in the challenge, but only top listed solutions will be considered for final presentations.

  • What would be there in the webinar mentioned in agenda? Is it compulsory to attend all the webinar sessions?
  • This is an online channel set up for discussing questions that the participants may have regarding the Datathon Challenge. We will fix a regular time during which IBS representatives will try to answer the questions. The questions can be posted to the group before the channel opens.


31 MARCH 2020


  1. A team could comprise of a minimum of 3 to a maximum of 6 members.
  2. All the team members should be from the same college/ institute. Students from any stream can participate in the challenge.
  3. Students should be able to demonstrate the solution in front of the Jury in an online or offline mode. The mode of demo will be shared via the website. (Powerpoint solutions will be rejected).
  4. The data and the full set of requirements will be shared as per the agenda.
  5. The solution will be judged on the criteria of innovation, impact, and readiness.



₹ 70,000


₹ 30,000