Skip to content

Three examples of transformational Data Science in the real world!

In our most recent data science blog post, we highlighted some of the innovative ways that organisations are driving value using data science. In this blog post, we’ll explore three real-world examples that showcase the transformational benefits that data science can have on an organisation.

Making sense of documents at scale

Organisations of all sizes process internal and external documents at varying degrees of diversity and volume – and for different reasons. A colossal task for government agencies like HM Passport Office or HMRC. The number of documents that these organisation process can become burdensome, resulting in increased costs, and reduced operational efficiency. Data science offers a unique solution.

Analytics Engines are supporting a non-departmental public body designed to stimulate the economy by driving innovation in the marketplace. The rising volume of applications led the client to consider a data solution to support their applications assessment team. They required a solution that would enable them to quickly identify duplicate or potentially fraudulent submissions and that could assign applications to assessors with greater efficiency than assessment and assignment by hand.

Utilising text analytics our solution automates the process of performing bulk document similarity checking for multiple submissions of the same application. In addition, the solution matches application topic areas with the skills and experience of an assessor to ensure a good fit. Prior to deployment of the solution, manual assessment and assignment of application took approximately 4 days to complete. Using our solution, the time taken to complete this process has been reduced from four days to just a matter of minutes.

Extracting insights from images and videos

When we think of data, most of us think of textual or numerical data, but images and video can be a valuable data source to organisations who need a visual lens. Using images and video to extract insights in a meaningful way can be manually painful. Computer vision can help organisations automate the process of extracting meaningful insights from images and videos.

Analytics Engines are supporting an organisation responsible for monitoring marine life populations. The client sought a technology partner to deliver an Artificial Intelligence (AI) system for object detection with tracking and counting capabilities for imagery of the seabed. Historically, this process was completed manually and was therefore time and resource intensive.

In response, we created a solution that utilises a range of advanced data-driven techniques and technologies including Artificial Intelligence and Computer Vision. This solution allows users to upload videos and images of the seabed and annotate an unlimited number of classes via a graphical user interface. This annotation platform includes semi-automatic annotation tools that help to speed up the annotation process. Once annotated, these images are used to train a custom model for the detection of a new class of objects and deployed to run on newly captured images.

The solution includes a tracker function which can track objects of interest across video frames that provides users with a running count of objects detected of each type as well as confidence scores for the classified objects. This technology will hugely decrease the efforts needed for the manual processing of image and video data and enable the digitisation of this process which can then be used for marine population monitoring and trend analysis.

Optimising and automating business processes

Artificial Intelligence and Machine Learning have become increasingly commonplace in recent years. A 2021 study by PWC found that 86% of respondents believed that Artificial Intelligence had become a mainstream technology. While the potential impact of these technologies cannot be understated, organisations must consider how these technologies align with their business objectives and whether an alternative approach can deliver the outcomes they need. Data science (along with the inquisitive data science team at Analytics Engines) can help organisations to make that decision.

Analytics Engines are supporting a US-based software organisation that offers services that help enterprise organisations gain insight into their use of hardware, software, SaaS, and cloud assets, enabling them to optimise their IT spending and realise maximum ROI.

The client was manually processing large volumes of data to identify what versions of software their customers were using. The client wanted to improve their efficiency and response time for their customers.

The client believed that a Machine Learning based approach could help to address this issue. Based on prior experience, however, our data scientists believed that an algorithmic, rules-based approach could deliver similar, if not better results. Our team also believed that a rules-based approach would help to eliminate many of the issues associated with a Machine Learning based approach including increased costs, more difficult deployment, and a need for ongoing maintenance.

To discover which approach would be most effective in the delivery of the project, we conducted an experiment using a sample dataset provided to us by the client.

We tasked both the Machine Learning Model and the rules-based Algorithmic Model with identifying and classifying the version numbers of the software contained within the sample dataset. From this test, we discovered that both the rules-based and Machine Learning approaches were able to match 86% of the records, however, the accuracy of the rules-based approach was 99%, while the Machine Learning approach was only able to achieve an accuracy of 70%.  What does that mean for their business? They can trust the results that they are receiving from the software is correct, enabling them to operate more efficiently and ultimately provide a better service to their customers.

Find Out More

Analytics Engines are experts in data science, data matching, search, integration, and visualisation. Our unique accelerator IP allows us to build and deploy solutions much faster, reducing time to value for our clients. We work in close partnership with you and your organisation to unlock the value in your data. We offer end-to-end guidance and support to help your business along its data journey. We build solutions that uncover decision-critical insights, address complex institutional problems and solve your most pressing problems. To learn more about how data science can support your organisation, contact us using the form below.

Share this article
by PJ Kirk

Fancy a chat?

Get in touch