How can life insurers address low persistency? How can data and analytics help?
We will demonstrate, with the use of a practical case study how the full cycle of actuarial analysis is evolving - from data collection and data enhancement, feature engineering, modelling, verification and ultimately application and communication.
We will provide an example application of data science applied to actuarial work including:
• Data preparation • Visualisation • Model fitting • Validation • Interpretation of results • Performance of fitted data science model relative to one or two alternative models.
The case study provides an introduction to generalised linear modelling and its use as a predictive modelling technique within insurance. We used open source programming software.
We will also touch on the potential to use external data, together with insurance companies data to build an enhanced persistency model of their book of contracts.
Join Actuartech and Adriaan Rowan & Rodwel Mupambirei on Thursday 12th March 2020 at 12 pm. Register here or visit www.actuartech.com/webinars for further information.
Machine Learning Application for Non Life Pricing and Profitability Analysis
Methods used in non-life pricing are evolving at a fast pace and more advanced actuarial and statistical techniques are being used in pricing, competition analysis and profitability analysis.
Machine Learning and AI techniques are the continuation of the evolution of tools and technologies used by actuaries and statisticians to analyse historical claims data with the aim of; improving the predictive power of models; solving the same problems with new methods; more data and computer power available.
Please join us as we walk through a practical case study of machine learning applications to non-life pricing and profitability analysis We will be comparing a set of statistical and machine learning models applied to non-life pricing.
We will be covering: Presentation and use of synthetic data to compare the modelsProvide an introduction to machine learning techniques used in non-life pricing and compare them on the synthetic data with the GLMs (pros and cons)Open new perspectives for product development (for example competition analysis and profitability analysis).
Join Actuartech and our subject matter experts, Xavier Marechal (Founder and CEO of Reacfin), Samuel Mahy (Head of the Non-Life Centre of Excellence at Reacfin) on Wednesday 18th March 2020 at 12 pm. Register here or visit www.actuartech.com/webinars for further information.
Introduction to Data Science in Insurance: Johannesburg
Training Event | 21 April 2020 | 10 am - 5 pm
There are a few remaining tickets available for our one day Data Science training event at the Hilton Sandton, Johannesburg. Register here
Event Overview Improvements in computational power have given rise to the use of data science techniques in a wide variety of areas, including finance, driverless cars, image detection, speech recognition etc. In a world of high volume and varied datasets, data science techniques are invaluable to an insurance professional's toolkit to provide actionable insights from data
An overview of the impact of Data science and possible applications within the Insurance Sector.
An understanding of the main techniques of Data Science including data management, machine learning, text mining, scraping and data visualisation.
Initial insight on how to address hot business topics in different fields of the Insurance Sector by leveraging data.
Who will benefit from the training? Actuaries or other insurance professionals working in insurance looking to learn how:
Improved data and computational capabilities can tackle insurance related business challenges with increasingly sophisticated approaches
The insurance professional can expand their toolkit by learning practical data science skills
Data Science can be applied in an insurance context, using practical business examples.
We will also provide a high level overview of the various machine learning techniques that are used covering the key supervised and unsupervised learning methods. This will include examples of how data science techniques can be applied in insurance.
Event Information Tuesday 21st April 10 am - 5 pm, Hilton Sandton Johannesburg
For further information or to register for the event click here.
Insurance & Insurtech Breakfast Johannesburg
Due to high demand, we have released a few additional tickets for our next round table discussion. 21 April 2020 7:30 - 09:30 am, Hilton Sandton, Johannesburg
The roundtable, hosted by Dupro and Actuartech, will bring together business leaders from Insurance and Technology - providing a platform for collaboration on the challenges and opportunities of the digital insurance technology landscape.
This event will explore opportunities created by new Insurtech innovations as well as look at how companies are responding.
Insurers have the opportunity to optimise their processes and create new sources of revenue by rethinking their traditional business models with the use of modern day technologies.
Key topics that will be discussed:
1. How will actuarial and finance functions adapt in the new digitally driven environment?
2. An update on the changing technology landscape given regulatory, statutory, operational and legal pressures including
IFRS 17, Impact of Data Science, and Digital delivery models
3. Emerging roles for finance leaders
1.Learn about the latest research in this field 2. Leave with an understanding of what digital technologies are and how developments are impacting the insurance industry from a finance and actuarial perspective 3. Appreciate the impact these developments could have on the finance and actuarial function of the future 4. Understand where organisations and individuals may need to change to benefit from the advances 5. Impact on the workforce 6. Interact with peers and colleagues in a discussion of this topic
Event Information Tuesday 21st April 07:30-09:30 am, Hilton Sandton Johannesburg
For further information or to register for the event click here.
Executive Data Science Sessions
Insurance Data Science Training | Executive Lunch Series
Introduction: The aim of the executive lunch is to support the leadership or executive team of a particular function or of the company to develop an awareness of the data challenges and opportunities the insurer is facing. It consists of round table discussions, over lunch on a regular basis. The lunches support the executive team to identify and develop key themes related to DataStrategy for their particular function.
The Goal of the training is for Leaders to:
Develop an awareness of Insurance Data strategy trends in 2020, for that particular function or leadership team
Share different perspectives and feedback about data topics within their team (s)
Enrich their understanding of data techniques and practices.
Depending on your requirements: we could also support teams to help define during the sessions1 or 2 business cases that would be developed in proof of concept mode in parallel to the duration of the training course and could be used to illustrate the practical themes of data science.
Examples Topics being covered:
An initial list of topics to be covered during the “Data Exec. Lunches”
Demystifying statistical learning models
How to identify key, valuable and realistic business cases for the company
From data governance and compliance to data efficiency and opportunities
Communication, storytelling and communication power in AI
Evolution of technologies and processes : operational, effective and scalable approaches
Demand Driven Innovation - Insurance Tech Lab is an industry-specific SME engagement programme which connects insurers with emerging technologies and early stage businesses that can solve real-world challenges to deliver measurable insights and ROI.
“Insurance techLAB’s framework introduces processes and technologies ensuring that insurers can increase value and efficiency and achieve a measurable ROI from their innovation activities.”
We live in a world of constant change and unlimited opportunity, where the insurance industry is constantly seeking to achieve and master transformational and value-added innovation, we see collaborative, ROI-focused innovation as the path which will shape the future. We have made it our mission to help forward-looking leaders in the insurance industry to collaborate safely, and effectively, with the innovators and emerging technologies that will shape the world of tomorrow.
Insurance techLAB is currently on-boarding insurers and programme sponsors worldwide and will solve industry-specific challenges ranging from efficiency to growth, compliance and value creation.
Please reach out to us to discuss the details of the programme and find out how Insurance techLAB can help future-proof the growth of your insurance company.
A practical example of data science considerations
A paper by the Modelling, Analytics and Insights in Data working party.
"Actuaries are increasingly looking to explore data science techniques as a way to deliver new insights, utilise new datasets and develop complex models efficiently. However challenges remain to integrate these new techniques into the standard actuarial toolkit. A key challenge for actuaries is to understand the steps involved in a typical data science project, including how to create a robust framework for developing and reviewing advanced statistical models. This paper presents an overview of the steps in a typical data science process and a worked case study provides a practical example the approaches taken to validate a machine learning model."
We offer a combination of structured, pre-defined courses or could tailor these to meet the needs of you or your organisation.
Enabling actuaries to embrace modern day data science tools and to work closely with data scientists is an important link that could give strategic advantages to insurers in the further development of actuarial modelling software.
Looking forward, the actuary will continue to evaluate key sources of data and need to find ways to incorporate data science that uses state of the art machine- learning and data technologies together with the actuary’s business insights. We need to refresh our methods and make use of emerging technological advances.
We can offer 8x1 hour lessons and, depending on the audience, this could either be structured as a ‘Foundations’ course focussed on the principles of data science or a longer ‘Foundations plus Practice’ course that includes practical training examples via the use of Jupyter Notebooks.
Clients would generally require access to a set number of training hours. Modules will be adapted to ensure relevant material and use cases for specific clients are covered. We can tailor this to suit your needs – contact us today: email@example.com
This talk took the form of an online webinar, with each of the speakers presenting, followed by a Q&A session.
Improvements in computational power have given rise to the use of data science and artificial intelligence techniques in a wide variety of areas, including finance, driverless cars, image detection, speech recognition etc. This is directly impacting business practices within the financial services through its application within banking, insurance and asset management.
It also gives rise to a wide range of ethical questions and the importance of integrating ethical considerations within business.
Why ethical challenges are increasing as the volume and variety of data increases?
The impact of ethics within data science
Emerging ethical issues within the field of AI
The role that technology can play
Exploring the changing role of professionals and government/regulators within financial services
Sophisticated machine learning models have the potential for high predictive accuracy but their complexity may sometimes result in black box models, which, in some cases, may appear to be a trade-off between accuracy and interpretability. For the actuary, the ability to articulate the outputs of a model is important and becomes crucial where models are used to inform important business decisions or where stakeholders need to understand the underlying dynamics of a system, and the impact of the results.
The presentation covered:
The importance of interpretability
What it means to have an interpretable machine learning model
Examples of approaches that have been used to provide interpretability
A practical case study showing an example approach to explain model predictions.
All of our webinars are available on demand and information regarding future webinars and how to register can be found by visiting our website www.actuartech.com/webinars
We are the home of actuarial technology for insight, training and networking.
Actuartech provides leading insights and research on the topic of actuarial technology.
We provide training, events and networking opportunities for anyone wanting to learn about the latest trends on data science, machine learning and actuarial related technology. We are based in the UK and have virtual hubs in other parts of the world.
We take technology and data science beyond the theoretical and can uncover, and explain, in simple to understand language the impact it will have and the problems we are trying to solve and ultimately what value it will bring to the organisation. We cut through the noise and bring you the simple, easy to understand insight and practical examples.
Ask us A Question
We are pleased to announce that our On Demand Consultation Portal is now live.
The portal is designed to provide start-ups, individuals and teams with valuable insight, advice and support, on the topic of actuarial technology, where and when you need it most.