idealo ( https://www.idealo.de ) is a Berlin success story: In 2000, we launched a mission to help our users make the right purchasing decisions. Today, we are one of the most popular German e-commerce websites with 1.5 million visits per day, around 58,000 shops and over 330 million offers and are one of the leading European shopping and comparison platforms. As a price comparison we are currently represented in six countries (Germany, France, Great Britain, Italy, Austria and Spain). Join our Meetup group to receive news about the technical talks, workshops, and other events that we host at our Tech HQ near Moritzplatz.
Some of the topics and technologies that our team and guest speakers are likely to talk about: Java, Scala, Python, open source, Mobile, product/UX, Kubernetes, AWS, machine learning, Big Data, Data Science, BI / Analytics, PostgreSQL/MongoDB, APIs, agile development and methodologies, and the cloud. Sure, that's a long list--but idealo is quite a complex operation! We use all of the above and more to create the best customer experiences for our users and partners.
This time we are hosting a very interesting topic about: "Using Deep Learning to rank millions of hotel images".
At idealo.de (a leading price comparison website in Europe) we have a dedicated service to provide hotel price comparisons (hotel.idealo.de). For each hotel we receive dozens of images and face the challenge of choosing the most “attractive” image for each offer on our offer comparison pages, as photos can be just as important for bookings as reviews. Given that we have millions of hotel offers, we end up with more than 100 million images for which we need an “attractiveness” assessment.
We addressed the need to automatically assess image quality by implementing an aesthetic and technical image quality classifier based on Google’s research paper “NIMA: Neural Image Assessment”. NIMA consists of two Convolutional Neural Networks (CNN) that aim to predict the aesthetic and technical quality of images, respectively. The models are trained via transfer learning, where ImageNet pre-trained CNNs are fine-tuned for each quality classification task.
In this talk, we will present our training approach and insights that we’ve gained throughout the process. We will then try to shed some light on what the trained models actually learned.
You can find the first write-up on https://medium.com/idealo-tech-blog/using-deep-learning-to-automatically-rank-millions-of-hotel-images-c7e2d2e5cae2 and the corresponding code on https://github.com/idealo/image-quality-assessment
1) Hao Nguyen
Hao is currently a Master's student at the Hasso Plattner Institute (Data Engineering) and a working student at idealo.de. His principal interests focus machine learning and deep learning. For his career, Hao just knows he wants to do something with data.
2) Christopher Lennan
Christopher is a Data Scientist at idealo.de where he works on computer vision problems to improve the product search experience. In previous positions, he applied machine learning methods to fMRI as well as financial data. Christopher holds a Master's degree in statistics from Humboldt Universität Berlin.
We are looking forward to seeing you @idealo!