I-COM Data Science Hackathons 2018
The 2018 Lufthansa Challenge
“What new KPI is a strong indicator of competitive digital strength and long-term sustainability as measured by market share and sales for Luftansa?"
As one of the world's leading airlines, Lufthansa has a very strong brand with stable positioning and sales, especially in Germany. Given the fundamental changes in marketing channels & technology and expected digital disruption happening in all industries due to digital transformation processes, Lufthansa is interested in identifying new KPIs that reflect digital strength and sustainability. This is to measure and improve the contribution of marketing towards digital transformation, apart from the digitalization of products and services.
Customer-centric and insight-driven marketing communication increases the perception of innovation and digital strength which in turn secures the longterm positioning of Lufthansa.
What is a KPI?
- Measurable value used to determine how well a company is achieving important business objectives
- Must be based on legitimate/accurate data and provide context for business objectives
- Characteristics of KPIs
- Quantitative: Can be measured
- Practical: Integrate with present company processes
- Directional: Help to determine if a company is improving
- Actionable: Used to make changes to improve towards business objectives
- A KPI should immediately inform how the business is performing which and should suggest what actions need to be taken
- What is not a KPI?
- Irrelevant to overall company
- Not actionable
- Big set of metrics
- Able to be manipulated
- What are good KPIs made of?
- Descriptive name
- Consistent calculation
- Target ranges of results
- KPI examples (Marketing)
- $ Customer Lifetime Value
- $ Customer Acquisition Cost
- % Brand Awareness
- % Net Promoter Score
- % Market share
Prediction task of the Challenge:
You will be presented with 3 years worth of airlines sales data originating in both the German and US markets. Your task is to predict weekly Lufthansa sales for each of the provided booking classes, from a specified 20 week time period using prior sales data across multiple airlines, as well as any of the provided auxiliary data you consider fit for the task. Each team will be evaluated by comparing their predictions to a holdout truth set using Mean Absolute Error as the evaluation metric. Any insights and signal learned between the auxiliary data and the prediction task may be used to support recommendations in the qualitative portion of the contest. You can use any data from the provided data sources for both the qualitative and quantitative challenge.
1st Round - 50/50 qualitative/quantitative weight
Final Round - 65/35 qualitative/quantitative weight
|Qualitative Scoring for the DSH 2018 Lufthansa Challenge|
|Each Hackathon team will answer the same questions within each slide deck.
Each question answered contributes to three general categories of scoring as outlined below:
|Business Value||Storytelling||Art & Tech|
|Main Theme||Does the solution address the client’s need?
Are there additional insights that are revealed beyond the key need?
|Did the team effectively communicate their solution and business application?||Can the solution scale globally and with more data?
Is the proposed solution elegant, creative and
|Scoring||0 - 4 Points:
0 - not able to link KPI to digital strength or longer term sustainability
4 - able to demonstrate the KPI is a strong indicator of digital strength, longer term sustainability and provide additional business value
|0 - 2 Points:
0 - not able to communication the value effectively
1 - able to communicate the value effectively
2 - adding more value with excellent communication
|0 - 3 Points:
0 - not able to demonstrate unique thinking, approach and solution is not scalable
4 - able to demonstrate extraordinary / unique thinking, creative approach and solution is scalable
|0 - 10 Points|