Tackle the most common challenge when developing data-driven solutions: How to define a tangible use case? The Supercrunchers will walk you through based on a real-life case.
Exploring how adapting multiple methodologies along with triangulation actually solve the puzzle of segmentation and impacts the big business drivers.
This paper describes the use of computerised topic analysis to segment and analyse tweets by US presidential election candidates in 2016. The statistical technique used to create the topic is called Latent Dirichlet Analysis (LDA). The paper shows how LDA can be used to automatically generate topics un textual data and discusses the potential to use LDA as both a static 'batch" and real time analysis approach for textual data.
In a world of Big Data and an ever-widening variety of data types, technological tools and infrastructure, while not glamorous, are mission-critical to insights creation and building a data-driven business culture. Microsoft's Market Research team (CMR) will share an innovative solution they developed to capture on-device product feedback that, when linked with terabytes of behavioral data, has generated insights to drive supply chain, product development and customer engagement decisions. This on-device measurement is part of the CMR's larger data management strategy, which brings together telemetry, survey data, and on-device measurement, using modern technologies like Azure, R, Machine Learning, and PowerBI, to generate and share knowledge that drives decision-making across Microsoft.
"How can we increase brand consideration and purchase intention." This is a fundamental question that any consumer brand faces. This is exactly what SONOS, the pioneer of the wireless home audio market, wanted to explore further. The first step was to radically improve the key driver modeling the approach to identifying why consumers buy. It turned out that conventional approaches are overly simplistic by assuming linearity, independence of drivers and neglecting indirect effects. We took the SONOS brand tracking data and built an advanced causal path modeling, using the universal structure modeling approach and the Neusrel software. What we found was that reality is much more different than conventional models force us to assume. The proof was that we achieved over 50% higher predictive power.
The story of how Orange created a 'pick-up-and-play' interactive experience to ensure new segment insight was heard, brought to life, and acted upon. For an insight manager developing a new segmentation, it is vital to not only think about the launch, but how to embed the segmentation. The worst case scenario is for it to sit on the shelf after the initial buzz. To overcome this, Orange & C Space created a 'Segmentation Toolkit': an interactive range of outputs and tools that drew inspiration from theatrical improvisation, psychology, and change management. This toolkit has changed how insight is viewed at Orange, and has promoted a customer and segment-centric perspective in the development of new products and services. We will reveal how to ensure insight isn't just heard, it's acted upon.
How SONOS boosted its growth trajectory by leveraging a universal structure modeling
One of the biggest problems any researcher is faced with today is reading. We can't read quickly enough. For numeric data there is an ocean of visualisation and analytics available, we can watch trends in 7 colours over 3 dimensions unfold on a smart phone. When it comes to textual data it is wholly different. Even small research projects can generate thousands of lines of text which we cannot hope to read thoroughly let alone summarise and understand. We need different forms of analysis for text and different visualisations. The paper shows via the analysis of tweets from USA Presidential candidates how Topic Analysis, using LDA, can be used to generate segments within unstructured information streams. LDA can be used on very large datasets, which is of significant importance.
In a world of Big Data and an ever-widening variety of data types, technological tools and infrastructure, while not glamorous, are mission-critical to insights creation and building a data-driven business culture. Microsoft's Market Research team (CMR) will share an innovative solution they developed to capture on-device product feedback that, when linked with terabytes of behavioral data, has generated insights to drive supply chain, product development and customer engagement decisions. This on-device measurement is part of the CMR's larger data management strategy, which brings together telemetry, survey data, and on-device measurement, using modern technologies like Azure, R, Machine Learning, and PowerBI, to generate and share knowledge that drives decision-making across Microsoft.