Case Study

Your needs matters.

Just because you built it does not mean they’ll use it. At Bayesianai, we understand the needs of your users and the necessary functionality to ensure you deliver the best user experience for your business goals.

Some of our recent work

Successful data science is all about understanding the problem you’re trying to solve. It’s not about black box solutions and wizardry!

At Bayesianai we place a lot emphasis on gaining a thorough understanding of our client needs before jumping into the code. Our focus is always on understanding what you do, what challenges you face and what your objectives are.

Below are some of the many data science solutions we have implemented over recent months. They are by no means exhaustive; please reach out to us to find out whether we can support your organisation.

Our solution architects help propose the right tools for every project to ensure a pragmatic approach to addressing your business needs.

Technologies We Use

Our team of engineering experts take a pragmatic approach to innovation and solving your business needs.

How do we design hospital layout?

Simulating patient flows using agent-based modelling.

We collaborated with Manchester University Hospital Trust on a simulation project to try to understand and minimise the spread of COVID-19 in hospitals

We designed an agent-based model in python that produces projections for under different conditions. This enabled us to understand the implications of different triage strategies and to quantify the risks.

How do we we choose the optimal location for a new store?

Predicting the impact of opening new retail centres in different locations

Our client wanted to understand the impact of new store openings across different locations. They wanted to know the ‘cannibalisation’ impact on their existing store network and where the best new store locations are.

Our solution was a suite of models that feed a user interface. The models provide predictions for the impact of store openings. The tool enables users to easily run simulations to investigate different scenarios of store location and store attributes.

What product bundles offer the best return on investment?

Customer lifetime value prediction using survival analysis.

A well-known publisher wanted to know which subscription packages delivered the highest value.

Should we offer monthly or quarterly subscriptions? Should this vary by region? What price point is optimal? What return on marketing investment will each subscription deliver?

They had an existing Excel-based solution in place, but results took a long time to generate and there were concerns about the accuracy of the results.

We built solutions that estimate subscriber retention, price elasticity and future value. Our client is able to simulate alternate scenarios and visualise the predictions using a custom-built dashboard.

How do we choose offer prices that maximise revenue?

Bayesian time series modelling to understand the trade-offs of alternate pricing strategies.

Our client, a wealth management company, wanted to optimise the prices they offered.

We built a data science solution that predicts the impact of different price points on net revenue, enabling them to build scenarios and make more informed decisions. The model uses Bayesian techniques, allowing them to understand prediction confidence.