Dataswarm analytic engine
FINDING THE ZEITGEIST
BBC: Needed “to understand the Zeitgeist” in real time across all media output in the UK and find the differences in memes and themes between its news output and the competitors.
COMBINING ENTERPRISE DATA
Large UK Telecoms Provider: Combined social data and customer services data and tailored its service operations to optimise the service delivery for customer satisfaction and retention
Global Cosmetics Co: Identified Zeitgeists to understand the differences and similarities in future trends between markets enabling focussed product development.
SALES & MARKETING
Global drinks supplier: Located customer sub-groups to understand the cultures and requirements to optimise product advertising messaging by geography and media type.
Real Time Monitoring
Receive alerts and specified data in real time about events, emerging trends, risks and issues e.g. for crisis management work.
Large Scale Systems
Integration and monitoring data sources of large scale systems such as Smart City and Internet of Things applications
Using system dynamics allows us to build self learning capability to improve analysis over time. We design bespoke client solutions for advanced business intelligence e.g. game theory based scenarios.
We have worked with major enterprises to integrate the DataSwarm insights and analysis into their end to end value chain to achieve their strategic goals.
The DataSwarm Analytic Engine (DAE) uses advanced analytics to create highly valuable business intelligence across all areas of the value chain. Core technologies include use of system dynamic methods, language processing, and high speed data analytics.
The system was originally designed to solve the problem of finding and sequencing trends and memes quickly and efficiently across vast quantities of media output, and can integrate social media, internal enterprise and "Internet of Things" datastreams. It is designed for flexibility and for example has been used for applications from front end social media analytics to back end customer service improvement.
The DAE is format independent, and so can work in most languages (human or machine).
Sales and Marketing
Expose deep industry trends and uncover sub-tribes. Build on memetic insights to develop campaigns with context. Crisis management applications in real time.
Pinpoint factors of customer satisfaction and discontent. Establish key drivers to predict defection and enhance customer retention.
HR & Internal communications
Highlight trending topics and trigger meaningful actions across the organisation. Build employee engagement and help with employee retention.
Product & Service Development
Detect and predict trends & memes across all industries to identify product demands enabling focussed product development.
We believe the best solutions require both algorithms and human expertise. Combining the DataSwarm Analytic Engine (DAE) with our deep consulting experience allows us to create solutions tailored to individual client requirements.
Dataswarm memetic analysis of German Election We have been tracking the German election using social media since February, and 6.8 million tweets later we have some predictions. Our Data Analytics Engine (which had correctly predicted Brexit, the US Election and the latest British one against the polls’ opinions) is now predicting for Germany….well, pretty[…]
The end analytics in diagrams, evening of June 7th – as you can see, the Tories & Labour are very close according to the system and it pretty much got it. So the UK election results are now known, Tories have 318 seats but needed 326 for a majority of 1. The Tory eventual vote[…]
Diagram showing more Tory memes in the top right, the memetic “sweet spot” of relevance and influence, There is a far higher intersection between “Theresa” and “May” than between Hillary and Clinton, which reduces her memetic impact. It’s the day before the UK general election, and our system is showing that on Twitter at any[…]
We have turned our system onto monitoring the British General Election (see diagram above), with some trepidation, for 3 reasons: Our system uses Social Media to predict elections, and in the UK in 2010 and 2015 Social Media was massively biassed towards the Liberals and Labour respectively, so the question for us is how biassed[…]
Well, we had hoped that things would become a bit clearer after the debate, but our DataSwarm Analytic Engine is still showing that Macron and Le Pen are essentially neck and neck, but with Macron losing his definite nose in front from earlier this week. As with last time, we thought we would make our[…]
Our DataSwarm Analytics Engine has been tracking the French Elections now for some time but since Sunday 23rd April when Emmanuel Macron of the ‘progressive movement’ En Marche! and Marine Le Pen (until that Sunday leader of the National Front – she temporarily stepped down in order to concentrate on being the presidential candidate) were declared[…]
Above – DataSwarm Analytic Engine – Zeitgeist memes for main participants in French election on Friday 21st april UPDATE We predicted it correctly, i.e. Macron & Le Pen, and in that order, but if you look above and read the “Underlying Analysis” below you will see we had a strange piece of data in that[…]
Last week we presented a talk at the Data & Politics conference in Berlin. It was a fascinating day, with a wide range of talks covering the Obama elections, how the German political ecosystem is dealing with fake news, bot etc, how data analytics is used in politics (cue lots of mentions of Cambridge Analytics)[…]
As you may recall, we had set our analytic engines onto election watching for Brexit last year , which it got right, and it also managed to predict the Trump election result . We have now set it onto watching the French and German elections, and will have something to say about the French one[…]
After our systems predicted Trump’s win, we were asked a number of times about the impact of Fake News (and Bots, Russian Hacking etc – we will cover those in separate posts) and here is a summary of some of the useful research we looked at: Stanford/ NYU Research Firstly, research by Hunt Allcott of[…]