Accurate “next basket prediction” will be enabling next generation e-commerce — predictive shopping and logistics. In this blogpost, we will discuss the deep learning technology behind next basket prediction and forecast the impact on online retailers and regular customers.
E-commerce is huge and online sales are predicted to double in the following three years. Covid19 pandemic accelerated this trend and now even groceries are going online. Many experts consider this process to be irreversible. Groceries particularly have many repetitive purchases occuring that generate patterns of buyer behaviour in time. …
In Recombee, we work hard on improving technologies for shopping cart prediction. Thanks to our customers like Bofrost, we are able to train our machine learning models on hundreds of millions of past purchases.
We have also recently partnered with NVidia to accelerate our deep learning research.
Searching for the right information has always been difficult. Not so long ago, relevant documents were stored in physical libraries and discovering them was a lengthy and complicated process.
When documents became available through online repositories, the number of indexed documents started to grow beyond physical storage limits. The same applies to the number of products offered by e-commerce sites or to content available through online streaming services.
Users tend to prefer finding everything in one place and most of them enjoy choosing from more relevant alternatives so service providers need to adapt. Global services (such as Google, Amazon, Netflix…
Lze předpokládat, že pandemie koronaviru a tvrdá opatření k jejímu zmírnění budou mít poměrně významný dopad na naši ekonomiku. Vše naznačuje, že přijatá opatření jsou v tuzemsku účinná. Odvrátila tak exponenciální šíření viru, zahlcení zdravotnického systému a předešla velkým ztrátám na životech. Zatím. Je jasné, že dokud nebude vakcína a společnost si nevytvoří rozumnou kolektivní imunitu, což může trvat roky, je třeba změnit způsob života tak, aby se i do budoucna zabránilo explozivnímu šíření viru. Pěkně to ve svém článku “Tanec kolem R” vysvětlil Tomas Pueyo. …
Academia is losing in its role of innovation leader as companies started investing heavily into fundamental research. It was not the case a decade ago (except pharma and few other domains) as fundamental research is costly for companies. Now, especially in AI, companies invest billions to win the race. It is hard to predict if funding large scale fundamental research in Deepmind, Google Brain or OpenAI with almost no direct business impact is sustainable in the long term, but let’s discuss its consequences for academia.
Brain drain from academia to industry is normal when it comes to students. …
Three years ago, our faculty started to support students with research ambitions. Since then, our summer research program has grown to over 50 participants from bachelor and master programs. This summer, each funded student has to write a blogpost about the research project she/he elaborates with her/his mentor. The research project is later finalized by submitting a research paper intended for a scientific journal or conference.
This publication will bring you interesting blogposts submitted by our students. We will release them one by one.
Automating machine learning is the topic of growing importance as first results are being used in practice bringing significant cost reduction. My talk at ML Prague conference maps state of the art techniques and open source AutoML frameworks mostly in the field of predictive modeling.
I have also presented our research that is being partially funded by Showmax within our joint laboratory at Faculty of Information Technology of the Czech Technical University in Prague.
I would also like to express gratitude for computation resources provided by Showmax, that make our extensive experiments possible.
Recommender systems are helping people not only to discover new content, but also stay in their information bubble. Here is how recommender systems work, so by recommending content previously visited by similar people (in terms of reading habits), one can easily discover content shared within an information bubble, but it is hard to find news written from different perspective for different audience.
It is a human naturel to construct theories and models of the world that…
@FIT_CTU, @DataLab_CTU, @recombee, @unico.ai