Join the Dynamic Pricing Competition

Bringing together academia and industry to compete in pricing algorithms.

Learn more

Join the Dynamic Pricing Competition

Bringing together academia and industry to compete in pricing algorithms.

Learn more

The dynamic pricing competition

Pricing is one of, if not the most challenging topics in the business world. It has huge impacts when it comes to making a loss or a profit. In today’s world prices are changed more frequent then ever before. Everyone involved tries to make the best use of data in the pricing decisions. But how are all these algorithms performing in the setting of competition with other algorithms, all in the context of uncertainty, incomplete information, and heterogeneous customer behavior? And after all, don’t forget the customer, they also have different objectives, follow patterns, and keep in mind they are not all alike.

Pricing combines all core challenges! Therefore, we want to bring together people from academia and industry from various backgrounds (Operations Research, Pricing & Revenue Management, Machine Learning & AI – Reinforcement Learning) to let their ideas and algorithms compete in various basic market settings. You will receive valuable insights on how your pricing strategy is performing: where it is good and outperforming others, and where is it lacking behind and gets beaten. Get the ultimate proof that your pricing algorithm is rocket science and unbeatable!

You don’t need to be a fancy programmer to participate, it’s more about concepts, strategies and approaches:
The minimal submission will only require a Python script with one function, see below example, which takes historical prices and sales data as input and returns a price to be used in the next iteration. Of course, within your function you can get as fancy and advanced as you like.  

The submitted algorithm will always be your property, we will never publish the code, we only use it exclusively within the competition. All algorithms will also be deleted from our servers after the competition. We only ask for a brief (not detailed!) description of your approach. These descriptions are only used in the performance evaluation, similar to the below paper with the results of the 1st contest edition in 2017 at the Informs RM & Pricing Conference in Amsterdam.

Note: The detailed specifications of the competition and the submission requirements will follow soon. Please signed up to the Email list to be first to get the information.

Example of a simple algorithm submission:
(simple dynamic pricing case: only competition, no capacity constraints, one product)

Organized by:
Stay tuned and be first to get updates

Register for the Competition here

important dates

Final definition of competition setup and deadlines

latest in March 2019

Start of training period

in May 2019

Deadline for final algorithm submission

in June 2019

Announcement of winners and publishing of results

July 2019

pricing scenarios
- More details are following soon -

Airline / Hotel Duopoly

A duopoly inspired by airlines, with finite capacities, a finite booking horizon, business and economy customers, and unknown demand function.

Retail Oligopoly

An oligopoly with unknown demand functions, where each seller has multiple (substitute or complementary) products on sale.

Core Dynamic Pricing

The 'simplest' challenge: a competitive market where each seller sells only a single product, with sufficient inventory and unknown demand function.


The demand models are NOT fully defined yet – wait for our specifications to come – but generally we will try to consider most of the following
You are faced with new and returning customers, returning customers are potentially aware of the price history and may act accordingly.
Also, customers are not all the same, you will observe some with high price elasticities and others who don’t care much about the money they spend.

general process

Signup (not open yet)

Simple registration: we will only require your name, email address, probably also a password for your login. There will a limit on signups and/ or algorithm submissions per participant, e.g. per participant only one algorithm per pricing scenario.

Development & Training (specifications are coming soon)

There will be a training period, approx. 30 days, where you can at night upload your algorithms. We perform training runs in which the algorithms already compete against each other. In the morning we will email you the logs of the nightly run.

Final contest & evaluation

The ultimate simulations runs are performed to identify and crown the winner. Full and detailed performance reports are generated and shared with participant.

WHY YOU SHOULD JOIN?

... apart from winning and proving you are best ...

Prize money

The winner of each pricing scenario will receive an economic prize of an amount of 500 EUR.

Detailed performance evaluation

You will receive a detailed performance evaluation of your algorithm and the competition.

Scoring & Benchmark

Get a scoring of your performance based on the benchmarks set by the other participants. Plus, an optional score entry of your algorithms on our (to come) "Leaderboard", similar to the netflixprize.

Similar to the 1st edition 2017, we will try to publish the results and findings of the 2019 competition again in a publication.

Paper on the 1st edition - Dynamic Pricing Challenge at the Informs RM & Pricing Conference in Amsterdam 2017

published in the Journal of Revenue and Pricing Management 2018

Organizer

 

For more information please contact:  info@dynamic-pricing-competition.com