Blogs home Featured Image

As Europe’s busiest airport, Heathrow safely carries hundreds of thousands of passengers through its terminals and onto their flights every day. Its busiest terminal, T5, carries over 30 million passengers each year. For this reason, even small advancements in planning and passenger efficiency can have enormous impact on total capacity for the airport as a whole. One such area is preparing for baggage that moves through the terminals, both from passengers travelling to/from London and passengers transferring onto onward flights.

The baggage operations team is responsible for monitoring and planning baggage flows through the airport and, in order to do so successfully, was working from a baggage demand forecast written in the Perl programming language. This forecast brought together flight schedules, predicted passenger numbers, and other airport information, which enabled the team to then put together a “prepared schedule file” and from this, the team could produce statistics on the expected baggage flows throughout the airport, and generate further outputs from models written in Excel that allowed predictions to be made for future travel and baggage demands. These demand predictions allowed planners at Heathrow to adjust resources accordingly to cope with future demand.

Challenge:

Some stages of this process, however, were input manually which meant that the Perl model was occasionally fragile in terms of input that it could cope with and, in addition, was difficult to maintain without experienced Perl developers available in-house, and errors difficult to interpret.

In order to better understand and interpret future scenarios, therefore, Heathrow needed a solution with increased automation in order to reduce error, while still having the ability to flag any problems with baggage thresholds.

Solution:

Data analytics consultancy, Mango Solutions, was invited to talk to members of Heathrow’s Baggage Architecture team who are part of the airport’s data analytics community of around 80-90 analysts about how they might address the challenge of increased efficiency.

Following discussions about the challenge, it was concluded that Heathrow would derive the most value from converting the existing Perl model code into R in order to automate the entire process to the point where little, or no, human intervention was required to produce outputs. This would then open up opportunities to increase the granularity – and therefore accuracy – of forecasting.

Using R, Mango helped Heathrow to build a modelling forecast for future baggage handling requirements based on historical patterns and future flight schedules. So, for example, Heathrow could look at historical data for a typical Monday in a given month in terms of types of passengers, the percentage of passengers that would likely check in baggage and the percentage split of business vs leisure travellers and marry that with forecasted passenger numbers for 5, 10 or more years hence. The option to model unplanned events and variants such as weather, air traffic control issues system problems and the impact these would have on flight schedule punctuality were also included in the model in order to help calculate the degree of baggage error that should be allowed.

A predictive model could now be built in order to understand what the future might look like for a particular terminal on a certain day in a month. Predicted numbers of passengers using check-in could be calculated along with the volumes of luggage likely on a flight and plans could be made for any physical constraints.

Mango also introduced random, unpredicted events into the schedule prompted by a ‘punctuality’ parameter, the aim of which was to simulate what would happen if flights were being delayed from a particular origin because of adverse weather conditions, for example, and how this event may affect incoming baggage.

“Automating multi-day forecasts, being able to test multiple scenarios and using simulations approaches to predict demand levels are small changes that will have an enormous knock-on effect on our airport. This new approach helps our teams to understand overall demand at Heathrow, giving us more accurate management of capacity as well as be proactive instead of reactive,” explained Mitchell Stirling, Capacity & Modelling Manager for Baggage Operations at Heathrow.

Results:

Since working with Mango to switch its strategic analytics language from Perl to R, Heathrow has begun to see tangible improvements and there is now a better understanding of future demand and capacity which will make the baggage operation more efficient and resilient, thanks to the inclusion by Mango of QC and diagnostics algorithms.

In the model demand between the arriving vs departing flights is more balanced than before. Heathrow can now read all input files, bring everything together and merge information based on their common identifiers to model future baggage demand throughout the day, attributed to direct flights and flight transfers.

In addition, by being better able to model future demand, Heathrow now has the ability to make the baggage handling process more efficient by targeting, resourcing or development more appropriately in its strategic Baggage roadmap and this, in turn, prevents unnecessary strain on onwards resources, such as security.

Mango Supports New development of ONS Data Science Campus
Blogs home Featured Image

The Data Science Campus (the Campus) is part of the Office for National Statistics (ONS), which is the government’s National Statistical Institute and the UK’s largest independent producer of official statistics. The Campus was created in response to the review of economic statistics published in 2016 by Professor Sir Charles Bean. The review recommended that ONS set up a national hub for data science to harness the power of big data to help Britain make better decisions and improve lives.

The Campus opened in March 2017 in Newport, Wales and plays a key role in developing one of the most digitally skilled populations of civil servants in the world through a range of learning and development programmes, delivered both directly and in collaboration with key partners in ONS, the Government Digital Service, industry and academia.

With its roots firmly planted in dealing with traditional, linear data, such as ten yearly census information, trend data or early economic indications data; the ONS’ remit for the Campus was to provide a fresh, ‘Silicon Valley’ feel technology environment for the Government.

Challenge:

The challenge for the Campus team was two-fold: how to get this initiative off the ground as soon as possible with minimal internal expertise available, and how to discover, define and estimate business aligned analytics projects and deliver them in a cost-effective manner to its key stakeholders.

Dave Johnson, Deputy Director for Knowledge Exchange, was tasked with setting up the Data Science Campus and Mango Solutions stepped in to help out.

Mango had recently been engaged by the ONS to modernise its analytic systems, so was already known among the ONS community and had earned a strong reputation for demonstrating real value. Following a tough procurement process, there was internal confidence that Mango were able to provide the necessary expertise to support the setup of the Campus.

Solution:

Mango approached this project from a long term perspective. Account Director Tim Oldfield said, “Rather than come in, do the work and then leave the team stranded, we came in for 9 months to spend time with the team, training them and advising them on best practise and approach so that, at the end of the 9 month period, a completely self-sufficient, extremely competent internal team were in place to continue the good work.”

Mango began by providing an experienced team of 3-5 data scientists to reside at the Campus in Newport. During the 9 months that Mango Solutions was in situ at the Campus, it tackled the challenge with a phased plan:

(i) Best practice analytic infrastructure
As part of Mango’s remit, the team were involved with developing a best practice analytic infrastructure for the team which included a Sandbox Data Lab environment, injecting commercial modelling techniques and algorithms into working applications. The team wrote reusable ONS packages including visualisations, report writing and libraries and trained and supported the team on their application.

(ii) Data science delivery
Mango built and mentored several production projects across the ONS including the United Nations funded Sustainability Development Goals, a system to monitor and measure world poverty based on 19 sustainable goals.

Two years on, the project has been scaled up and is now being used by other countries including the United States, Armenia and Rwanda, and is being further developed in to a fully-fledged website by the Sustainable Development team at ONS.

(iii) Build the analytic community
Mango supported the set-up of an analytic community within the Campus and helped to showcase the team’s capabilities across the organisation; on the use of analytics tools as well as methods of best practice for data science frameworks. Mango then helped the team to develop this community by sharing examples of best practice and engaging with the business by presenting internally on agreed data science topics to stakeholders. The team at ONS now facilitates collaboration, ideas sharing and best practice frameworks with a common language for data science delivery.

Results

Mango’s early strategic advice, defining processes and frameworks with established outputs has had a considerable impact at a global level. Explained Oldfield: “Mango helped to ensure the Campus was up and running within 6 months and have helped to shape the foundation to where they are today. We have brought meaningful results within a short timeframe, establishing a process for operational data science from scratch – the catalyst that jump started and framed the achievements to where the Campus are 2 years on.”

The Campus’ capabilities are now supporting other Government departments, academia and industry as well as international institutions.

‘As part of their network, the Data Science Campus is working to push the boundaries of data science research within ONS, their partner networks across the UK and beyond’, said Oldfield.

 

Blogs home Featured Image

About our client

This multinational retailer has been a leader in the retail space for more than a century and have 1000+ stores in 50+ countries.

The challenge

Our client engaged us to help them with their journey towards becoming data-driven. After focusing a significant amount of resource toward wrangling their data and building a Data Science team, there was still a gap – even with all of the tools available, the data wasn’t being used to solve business problems.

After meeting with the Head of Enterprise Analytics, we identified that the business team and the analytics team weren’t communicating. While the analytics team spoke about algorithms, the business team spoke in terms of business challenges. This lack of a common language meant the two teams were working in silos and all potential data-driven work stalled.

The solution

In response to this challenge, we developed a workshop –The Art of the Possible– that would bridge the gap between the two teams. Our experience helping organisations develop data-driven strategies enabled us to develop interactive and practical exercises that encouraged the analytics and business teams to work together, assisting the analytics team to understand how the business worked and helping the business side see how they could identify and qualify analytics use cases across the business.

The results

In each of these workshops, the business team often identify a minimum of 10 analytic use cases that can be used to make improvements across the organisation. This positive step means the teams can work together to shape how data is used and business challenges can be solved using concrete data.

Our work with this client is ongoing; Chief Data Scientist, Richard Pugh, works with the teams regularly throughout the year to help them further their data-driven journey.

We’ve been helping businesses build Data Science capabilities since 2002. From helping your team find a common language to supporting the hiring process and advising on optimal ways to optimise your processes to drive decisions, we can work with you to find the best solution.

Talk to us about The Art of the Possible workshops and becoming a data-driven organisation: sales@mango-solutions.com

Blogs home Featured Image

The Bosch Group is a leading global supplier of technology and services. Its operations are divided into four business sectors: Mobility Solutions, Industrial Technology, Consumer Goods, and Energy and Building Technology. Mango Solutions were approached by the new ‘Powertrain Solutions division’, which focuses on injection technology and powertrain peripherals for internal-combustion engines, diverse solutions for powertrain electrification.

The Challenge

Bosch had a diverse team of R users, some with limited R experience and others with a more advanced knowledge base. They wanted the new ‘Powertrain Solutions division’ team to all be on equal footing in order for the team to function in a streamlined manner. This was especially important as the team is based over several locations.

The Bosch team also wanted to be able to present key insights from their work to management in a clear and easy to understand format. They knew that management just needed to be presented the main facts in order for them to make decisions.

The Solution

Mango helped Bosch’s team level out their R skills in two phases of training.

Phase one was an intensive training programme that covered an introduction to R through to advanced R. By taking the full team through the whole course they could leave knowing all members were now able to work with equal understanding and skills.

Phase two focused on visualisation and improving communication between the Data Science team and management. This phase included workshops that gave users an introduction to Shiny. The Shiny training enabled the Data Science team to create Shiny dashboards, which they could use to present their insights in easy to understand visualisations for the management team. The gap in communication between the Data Scientists and management had now become bridged. The training has allowed Bosch to move quicker in making powerful business decisions which are fully backed up by accurate data science work.

Results

The ‘Powertrain Solutions division’ now have a unified approach and understanding of R and are better equipped to work as a team and communicate across different locations.

Importantly, management can now make informed data-driven decisions quickly. The Shiny training has enabled the data science team to present their work to management in a shorter time-frame and with clearer business recommendations.

Blogs home Featured Image

Covance Inc. is a global contract research organization and the world’s most comprehensive drug development company. They provide high-quality non-clinical, pre-clinical, clinical and commercialization services to pharmaceutical and biotechnology companies to help reduce the time and cost associated with drug development.

Covance’s analysts are predominantly mathematicians performing patient recruitment forecasting within SQL and Excel.

The Challenge

SAS is a legacy program used at Covance, but impressed by the popularity and flexibility of R, they approached Mango Solutions to assist them in understanding how it could be used within their modelling department. Because R offers faster processing and higher quality clinical trial simulations the team were keen to develop their R skills. Covance also wanted to look at improving the appearance of the graphics they create, and, where appropriate, deploy those to management using the Shiny package.

The Solution

After initial discussions with the Clinical Informatics team at Covance, we recommended a tailored R training and Shiny course. The course was highly interactive, with exercises throughout to reinforce the training. Comprehensive course notes and post course support were provided to each attendee to further support their usage of R and Shiny beyond the classroom.

Mango Solutions have been delivering R training since 2002; since then we have trained many thousands of people. Our experienced trainers are all data science consultants working on real-world R solutions; this ensures they have a wealth of technical and commercial experience and knowledge across a range of sectors and industries. This unique mix of experience and an existing relationship with Covance through non-profit organisations, such as PSI, placed Mango in the perfect position to assist the team with their training and development requirements.

The Benefits

The training delivered by Mango empowered the Covance team to move away from Excel and create enhanced, interactive, visual reports with their data. This enabled them to provide their management team with graphics that were easier to understand and navigate. The team were then able to apply their new skills to develop a prototype which was entered into the Fierce Innovations Awards, winning in two categories: Business Intelligence/Data Analytics and Best in Show (Best Outsourcing Partner).

Blogs home Featured Image

Pfizer is one of the world’s largest research & development biopharmaceutical companies, striving to set the standard for quality, safety and value in the drug development and manufacture of health care products. Pfizer’s global portfolio includes medicines and vaccines as well as many consumer health care products. Pfizer colleagues work together across a wide range of medical disciplines to advance wellness, preventions, treatments and cures to bring therapies to people that extend and significantly improve their lives.

The Challenge

Pfizer has been using model-based meta-analysis (MBMA) as one of its strategies for decision making in their drug development. In many disease indications, there is an immense amount of publically available information on approved drugs as well as those currently in development. Accumulation and integration of this clinical trial data is very useful to understand the disease and treatment options. Quantification of the efficacy and safety of those available treatments and then benchmarking such data with an investigational drug provides invaluable information for critical decision making for development teams.

Since 2006, Pfizer has been developing literature databases covering more than 70 disease indications. They use a third party provider to extract data from publically available information sources (e.g. journals, conference proceedings) to digitize into standardized datasets. Pfizer has developed a standardized process for literature search, review, data capturing and archiving into its central repository thus enabling a high quality and consistent format. However, the majority of the data cleaning and curation process is still a manual process; the analyst needs to check the data, go back to the original paper if necessary and make the final data selections for data curation so that the dataset is ready for analysis. As such, the cleaning and curation process can be both difficult and time consuming. Pfizer required a user friendly (yet easily modifiable by the end user) application to assist with this process.

The Solution

The key aim of the application was to provide the users with an easy to use visualization tool for data cleaning and curation. Mango worked with Pfizer to understand and prioritise features of the application and delivered many of these initial features plus more than the original requirements in a proof of concept stage using the R framework for web applications: Shiny.

The newly designed interface allows users to quickly view the plots by paper, and users can switch the endpoint for the plots or create multi-panel plots by selecting x- and y- variables. It also adds flexibility to select (or de-select) columns by just few clicks and the column names (encoded) are matched up with column descriptions for easier selection (or de-selection). When it came to selecting the data point, the users had even more functionality, all based around an interactive graphic and table powered by Shiny. For example, users are able to select rows by simply clicking the point on the graphic with zoom and pan features making it easy to distinguish between points. Alternatively by scrolling through the table and selecting a row they could remove it from the data. The tool was implemented in R using Shiny meaning that the code is easy for end users to modify.

Business Benefits

The Shiny MBMA tool created by Mango has facilitated the process of data cleaning and curation, making it quicker, easier and more efficient for analysts at Pfizer. This is all done within a single application; after uploading the data in to Shiny app, the analyst is able to view the plots, clean the data, and select the columns with the interactive interface. Then the analysis-ready data can be exported. Further analysis stages can easily be added on to the application in the form of additional screens at any time as required.

The Shiny application provides benefits for the MBMA process, it saves tremendous time and effort as the quantitative understanding of the disease is critical for decision making in drug development at Pfizer.

‘The data cleaning and curation for MBMA was time-consuming and cumbersome because we needed to go back to the original paper to make sure that the data was correctly captured, and we need to understand what exactly was captured in the dataset out of more than 200 columns. This app makes it so much easier to create plots, check the data, and select/de-select the data points or columns we need for analysis. The app also has one click button to create a BibTex file (bibliography for the dataset), which saves us a day of tedious work.’

 

Hiscox Case Study
Blogs home Featured Image

Headquartered in Bermuda, the Hiscox Group employs over 2,700 people in 14 countries. Through the retail businesses in the UK, Europe, Asia and the US, the firm offers a range of specialist insurance for professionals, business customers and homeowners. Hiscox UK has over 100 years’ experience in insurance, protecting businesses of all sizes as well as home insurance cover for over 60,000 homes in the UK.

Challenge

For the insurance sector, data analysis is in the DNA. With accurate, risk-based pricing a key capability for successful companies, Hiscox embarked on a data journey that would enable a step change in the way it uses data and analytics to increase efficiency and add value for customers.

It was the job of Steven Wilkins, group head of Hiscox’s Data Labs team, to secure buy-in – both cultural and financial – from the firm’s senior leadership team. He aimed to demonstrate the value-add to the business of increasing investment in data analytics and build the case for further investment.

To support this goal, Wilkins decided to enlist the support of a specialist consultancy.

“Data is a strategic asset,” explained Wilkins. “We have the skills to use a broad spectrum of data to improve business decision-making and create more value for customers and shareholders. But we needed help with specific high value-analytics and in instilling cultural change across the business.”

Solution

It was the need to drive cultural change that led to Wilkins selecting Mango Solutions as a strategic partner – despite meeting with numerous consultancies’. “Many of the Big 4 pitched large projects with significant headcounts. Mango emphasised the need to transfer knowledge to Hiscox and this is the real value add – long-term capability growth. We just loved Mango’s transparency; we could have very real and honest conversations about what would and wouldn’t work.”

Mango’s ability to scale and its pragmatic approach meant that Wilkins was comfortable testing the water with smaller projects, without feeling under pressure to work at an unrealistic speed: the firm needed to execute well on these projects and showcase the benefits of a data-driven approach.

“It came down to selecting a partner that could understand the firm’s operating model and deliver tangible results quickly,” Wilkins explained. ‘We knew that getting the engagement right would also prove important in the longer term: Mango helped us with the small projects we needed to start with and also built enthusiasm for data in order to achieve the cultural change – and their engagement with Hiscox has grown over time.”

Approach

According to Mango’s Rich Pugh, the success of these projects hinged entirely on the execution of a cultural transformation within the firm and on the upskilling of staff and internal training. Mango worked with Hiscox to run education programmes for the leadership team and other key areas of the business – inspiring people by exploring the possibilities of advanced analytics. Mango also advised Hiscox on its use of core technology, including work on the R operating model and the POLO platform, to ensure the team was deriving maximum return on the project investment.

With this process of cultural transformation and training in place, Mango then supported the firm on several digital transformation projects:

Greater personalisation of service: Hiscox wanted to offer the most appropriate, relevant products to its customers and Mango was tasked with three key business challenges:

  • Do we understand customer habits well enough to ensure they are adequately insured?
  • When the phone rings in the Customer Experience Centre, who should take which call?
  • How do we ensure every conversation is personalised and offers a true value exchange?

Mango took millions of rows of data and built a system which answered these questions, enabling staff to hold better conversations and come up with valuable recommendations. The analysis also offered insights into pricing policies and product buying habits.

Resourcing modelling: There are around 250 claims handlers in Hiscox and it’s important to understand how that resource is managed and how it evolves in terms of efficiency and customer satisfaction. Using analytics, the firm ensures the most efficient resourcing by adding historical data into the equation – this might include extreme weather patterns which influence numbers and types of claim, or seasonal changes which required more or less resource.

Reporting back to the business on resource requirements for particular time periods was a powerful way for Wilkins’ team of six to demonstrate how data analytics can provide the insight required to make sound commercial decisions – “Here’s a business decision which we can go and change.”

Results

“It’s been about focusing on the right data and getting value out of what we are investing in,” said Wilkins. “As a key reinsurance market, we have access to large data sets: we needed to get value out of those and really understand our clients – differentiating our offering through advanced analytics.”

“We have been working with Mango for two years and we’re now seeing tangible traction in the use of data,” explained Wilkins. “We love the pragmatism of Mango’s data consultancy – we’re not investing 6-figure sums into projects, but working through milestones to really achieve something. We also like having Mango consultants working alongside our teams, really getting value out of the projects we are working on but also sharing knowledge and upskilling our current team. That’s a real partnership that has allowed us to progress and achieve a significant return on our investment.”

Future plans

Due to the success of the initial projects Mango undertook for Hiscox, Wilkins has been able to demonstrate the real value of being a data-driven business to the leadership team and secure budget for more projects and resource. Wilkins admits there is still a long way to go before Hiscox can call itself data-driven, but he has buy-in from the leadership team to keep progressing and looks forward to working with Mango on further projects – both big and small – across the company.