Month: April 2021

Working with data – Valkuren’s way

The first step of working with data is data acquisition. At an early stage we realised that data extraction from the whole range of sources our clients use, would be a key component of our everyday work. As companies grow, their data grows as well. It grows in volume, density (volume/time) and complexity. So, what might first seem as an easy-to-do, manual operation soon turns into a major, hard-to-handle big data process.  

 

That is why, Valkuren came up with its solution. The data would be extracted and tabulated automatically by a workflow mechanism, Apache Airflow, on Amazon Web Services. This workflow would be a composition of DAGs (Directed Acyclic Graphs) we could switch on and off as needed. A DAG is a collection of all the tasks you want to run, organized in a way that reflects their relationships and dependencies. Each DAG would represent one of the sources of data, for example, if a company extends its marketing campaign in social media such as Facebook and Instagram, there would be a DAG for Facebook and a separate one for Instagram; if the company sells using an online platform such as WooCommerce, a graph representing it would be introduced. Each DAG would be made up of the variety of processes in the data workflow. If we consider the example of Facebook, the graph would start with the data extraction (respectively for posts; page insights; etc.) from the social medium’s API, afterwards the data would be transformed to adapt to our visualization and analysis needs and finally it would be saved in tabulated form as required.  

 

Each graph has 2 variants of running, either a one-time run or an incremental run. The one-time run DAGs were only used at the start of our automated work, whereas as the incremental DAGs run once a week so as to extract, transform and save the observations of the week and therefore incrementing our data volume. 

 

 

However the automation of the workflow is not and will not be our only challenge in this developing field, that is why we are always changing, growing and improving, with the single purpose of unlocking the power of data. 

Writing by Uendi Kodheli data scientist @Valkuren

The recommender system in e-commerce

 

A recommender system is a filtering process which consists of suggesting relevant information to users. Rather than showing all possible information to a user at once. In the case of an online store, the purpose of a recommender system is to offer the customer, products or services, adapted to his profile. This process filters the information to a subset based on methods such as Collaborative filtering, Neighbour-based Collaborative filtering, and Content-based filtering. 

 

Collaborative filtering methods for recommender systems are methods that are solely based on past interactions recorded between users and items to yield new recommendations. The main idea is that past user-item interactions are sufficient to detect similar users and similar items to make predictions based on the estimated proximities. The main advantage of collaborative approaches is that they require no information about users or items and, so, they can be used in many situations. 

 

Content-based methods, on the other hand, use additional information about users and items. These methods try to construct a model based on the available features on the items, that justify the observed user-items interactions.

  

Several factors have influenced the use of recommender systems. The growth in digitalization, the increasing use of online platforms, and the abundance of online information has accentuated the importance for businesses and organizations to offer the right information, whether that be a product, a service or content, to the right user at the right time. Recommender systems meet this need, and have many benefits such as improve customer experience, not exclusively through relevant information, they additionally offer the correct advice and direction. Thus, engage and increase user interaction, and create the ability of tailoring and personalizing offers to users, which could ultimately lead to increase revenue depending on the business. 

 

At Valkuren, we implemented this recommender system for an e-commerce platform to optimize the consumer experience on our client’s website. We used the predictive method to improve the product offering to consumers based on their search using purchase history and estimated proximity.

 

Feel free to contact us for more detail!

 

 

Welcome Back !

We are very pleased to announce that the Valkuren team is growing. Magnus, our former intern & job student in Data Science, is back with us. We let him introduce himself.

 

 

We are very pleased to announce that the Valkuren team is growing. Magnus, our former intern & job student in Data Science, is back with us. We let him introduce himself.

 

Having recently graduated from a Master’s Degree in Data Science for Decision Making at Maastricht University, I am extremely excited to join the young team at Valkuren as a Junior Data Scientist. Passionate about data-driven decision making and problem solving. I started my higher education studies at Bordeaux University in Mathematics and Computer Science. This gave me the fundamental learnings to further pursue my studies in Data Science, and the motivation to face new challenge in a completely new environment in Maastricht.

 

During my Master studies I did an internship at Valkuren with a project at the STIB-MIVB on a predictive maintenance project. I helped the Data & Analytics team to design a functional pipeline to predict future wear and tear of tram wheels.

 

Once my internship came to an end I continued working part-time for Valkuren alongside my Master thesis, and designed the methodology for future data science projects.

I now join Valkuren full-time. The opportunity to jump start my career, continue learning and grow simultaneously with the company was extremely appealing.

 

What do you enjoy doing in your spare time?

 

At the end of the day I enjoy to wind down with a book, currently I’m reading Mick Herron’s spy thriller series ‘Slough House’.

Currently I’m spending my evenings finishing up an article on my thesis research for publication. My work proposes a new methodology for the classification of single-cells using a new feature selection algorithm.

Other than that, I enjoy traveling and spending my time outdoors with friends.