In die Kategorie Analytics fallen sowohl die klassischen Data-driven-Business / BI-Themen (Data Warehouse, ETL, Reporting, Dashboards) als auch die neueren Trends in diesem Umfeld: Big Data, Data Science & Deep Learning und Search-based Applications.

Wir verstehen uns als Spezialist für anspruchsvolle Aufgaben in den Bereichen Data Management und Analytics, die unter Zeitdruck gelöst werden müssen und für die oftmals in den Unternehmen keine eigenen Fachleute verfügbar sind:

  • die Modellierung hochkomplexer Cubes,
  • die Integration heterogener Datenquellen,
  • der effiziente Umgang mit sehr großen Datenvolumina (Big Data),
  • die wissenschaftliche Analyse dieser Daten-Pools (Data Science) und
  • der Einsatz von innovativen Suchtechnologien im Unternehmenskontext.

Causal Inference in Campaign Targeting


In this article I will work through a synthetic example to show the efficacy of causal inference in marketing campaign targeting.

The following is one of two posts published alongside the JustCause framework, which we developed at inovex as a tool to foster good scientific practice in the field

Causal Inference in Campaign Targeting2020-05-13T16:18:46+00:00

Blockchain-Lösungen für den produktionstechnischen Mittelstand


Die Digitalisierung findet Einzug in den deutschen produktionstechnischen Mittelstand. Bisherige Ansätze beschränken sich auf die Optimierungen firmeninterner Prozesse. Der nächste Schritt ist die Nutzung dieser Ansätze, um firmenübergreifende Geschäftsmodelle zu realisieren.

Hinweis: Der folgende Artikel ist zuerst im Onlinemagazin wt Werkstattstechnik, Band 111 (Nr.4), S.201-204, 2020 erschienen. Die Digitalisierung findet Einzug in den deu

Blockchain-Lösungen für den produktionstechnischen Mittelstand2020-05-18T17:46:42+00:00

End-to-End Image Captioning


We had the unique opportunity to develop an image captioning system combining computer vision and NLP from a prototype model to a fully scalable data product with a team of five interdisciplinary students from the TUM Data Innovation Lab during a period of six months as part of an educational research experience.

tl;dr Data Science, Machine Learning Engineering, Software Engineering, and IT-Operations know-how is required to turn a prototypical machine-learning model into an end-

End-to-End Image Captioning2020-05-01T15:23:28+00:00

Causal Inference: Introduction to Causal Effect Estimation


Recently, there has been a surge in interest in Causal Inference. It is, however, not always clear what is meant by the term and what the respective methods can actually do. This post gives a high-level overview over the two major schools of Causal Inference and then dives deep into the basics of one of them.

Recently, there has been a surge in interest in what is called Causal Inference. It i

Causal Inference: Introduction to Causal Effect Estimation2020-03-23T12:55:32+00:00

SocialVisTUM: Visualize and Label Clusters of Social Media Texts


We developed SocialVisTUM, a new user-friendly visualization and labeling toolkit which enables users to get a quick and comprehensible visual overview of topics and topic relations for any English text corpus and can be accessed online. Read on for the details and an interactive demo!

Web sources such as social networks, internet forums, and user reviews, provide large amounts of unstructured text data. Due to the steady development of new platform

SocialVisTUM: Visualize and Label Clusters of Social Media Texts2020-03-16T10:10:26+00:00

3D Deep Learning with TensorFlow 2


In this blog post, we will first have a look at 3D deep learning with PointNet. Its creators provide a TensorFlow 1.x implementation of PointNet on Github, but since TensorFlow 2.0 was released in the meantime, we will transform it into an idiomatic TensorFlow 2 implementation in the second part of this post.

The world that we interact with each and every day is three-dimensional, but the majority of deep learning models process visual data as 2D images. However, there are

3D Deep Learning with TensorFlow 22020-03-09T17:36:48+00:00

Prefect: Das zeitgemäße Airflow?


Prefect ist ein neues Workflow-Management-Tool das Airflow den Kampf angesagt hat und es mittelfristig von der Spitze verdrängen will. Mit einer leicht verständlichen Einführung erfahrt ihr hier, ob das Projekt seinen Ambitionen gerecht werden kann.

Was nicht passt wird passend gemacht! Das dachten sich vermutlich die Entwickler von Prefect, als die Idee für ihr Projekt entstand. Es will sich als eine Art Weitere

Prefect: Das zeitgemäße Airflow?2020-03-09T17:38:01+00:00

Machine Learning on the Edge for Parking Guidance Systems


Machine Learning on the Edge becomes more and more important for Smart Cities. We investigate how Deep Learning models can be optimized and deployed on edge devices for smart parking guidance systems.

This blog post investigates how deep learning models can be optimized and deployed on edge devices for parking guidance systems. I will present two different approach

Machine Learning on the Edge for Parking Guidance Systems2020-01-07T15:42:43+00:00

Recognizing & Assessing Recurrent Human Activity with Wearable Sensors


I used the distributed sensor system SensX to detect, identify and assess the quality of human motion in workouts. This article introduces the sequential process chain I implemented for analyzing multi-dimensional time-series with algorithms of supervised machine learning.

The visions created by the Internet of Things, which encompass the seamless embedding of the virtual world into daily human life have become reality by now. In that c

Recognizing & Assessing Recurrent Human Activity with Wearable Sensors2020-03-09T17:39:40+00:00

Transfer Learning for Text Classification with Siamese Networks


In this blogpost, I want to present my master's thesis, which focused on transfer learning for text classification using Siamese Networks.

Text classification is a field in natural language processing (NLP), which assigns text to given classes. With applications in sentiment analysis, spam detection or i

Transfer Learning for Text Classification with Siamese Networks2020-03-19T10:02:10+00:00

Uncertainty Quantification in Deep Learning


Teach your Deep Neural Network to be aware of its epistemic and aleatory uncertainty. Get a quantified confidence measure for your Deep Learning predictions.

Artificial Intelligence—and machine learning in particular—have come a long way since their early beginnings. The widespread availability and affordability of powerfu

Uncertainty Quantification in Deep Learning2019-10-09T14:17:31+00:00

Multimodal Sequential Recommender Systems


Sequential recommender systems are based on sequential user representations for a given user and sequence length. Each sequence consists of several items in temporal order. Sequential recommender systems aim at exploiting the temporal information that is hidden in the sequence of item interactions of the given user.

Since the invention of the internet, the availability and amount of information has increased steadily. Today we are facing problems of information overload and an ov

Multimodal Sequential Recommender Systems2019-09-02T14:54:44+00:00

Turnilo: A Lightweight Frontend for Realtime Analytics Powered by Apache Druid


In this post, we introduce Turnilo, explain its configuration and usage and share our evaluation outcome. For completeness, we also provide a list of current alternatives.

We frequently help our customers implement data platforms on a grand scale: as a backend for user-facing applications, for business analytics or data science and mach

Turnilo: A Lightweight Frontend for Realtime Analytics Powered by Apache Druid2020-03-09T18:01:39+00:00

Digitize your Receipts using Computer Vision


In this article I describe the steps and approaches to image recognition for receipt digitalization using computer vision. This is the basic functionality behind apps such as Google Lens, Evernote, PaperScan and

“Would you like the receipt?”—It’s hard to say no to that. Not because you actually want it (you may even throw it in the trash before exiting the store), but because

Digitize your Receipts using Computer Vision2019-08-08T13:00:31+00:00

Summarizing Long Texts with Seq2Seq Neural Networks


We extend state-of-the-art  sequence-to-sequence neural networks for summarization of long text across windows. By learning transitions, we are able to process arbitrarily long texts during inference.

This blog post describes my master thesis "Abstractive Summarization for Long Texts". We’ve extended existing state-of-the-art  sequence-to-sequence (Seq2Seq) neural net

Summarizing Long Texts with Seq2Seq Neural Networks2019-07-08T09:24:24+00:00
Mehr Beiträge laden