Blog Archives

17 Aug 2022

5 Essential Aspects of Credit Risk Model Monitoring for Probability of Default (PD) Models

Probability of Default (PD) models are a mathematical means of assessing how likely an obligor is to default on a credit obligation. The scorecard models are composed of quantitative and/or qualitative factors, which are considered indicators of how likely an obligor is to default. The idea is that when all factors are taken together in […]

17 Aug 2022

Climate Panel – Can tech save the world?

This session, hosted by Laurence Watson, covers 4 lightning talks, followed by a Q&A panel discussion.  Accelerating action on climate change with data (Laurence Watson) Subak works with innovative data-driven non-profit organisations to move the needle on climate. We believe open data is a key driver of innovation. However, too often in the climate sector, […]

17 Aug 2022

Predicting Food Preparation Time at Deliveroo

Understanding when food will be ready is integral to delivering food to customers on time and ensuring our delivery riders time is well used. This talk will dive into how we predict food preparation time at Deliveroo despite not receiving direct feedback from our restaurant partners when food is ready to be collected.

17 Aug 2022

End to end Data Science on Databricks

Developing a model is only a small part of successful Data science project. Successful data science project also includes efficient data preparation and exploration, extensive modeling and tuning, controlled production deployment, extensive monitoring and model retraining, as well as governance of the entire process. In this talk we’ll look into productionization of data science products […]

17 Aug 2022

Time Series Forecasting with Python – Predicting Flu Incidence in 50 US states

GitHub Repo for this session: https://github.com/ltsaprounis/dsf-ts-forecasting Join us to experience the end-to-end workflow for a real-world time series forecasting project using python. In this hands-on workshop we’ll take a real-life dataset containing over 50 time series for Influenza like Illness (ILI) incidence in the US and look at how to produce the most accurate forecasts. […]

17 Aug 2022

Data collection should make users happy first, and enable supervised learning second

It’s often hard to get started with a supervised learning problem without much/any data. But the way you collect data can be annoying and intrusive for users. Collecting data carelessly can therefore drag user metrics down, and reduce data quality, because the people providing it simply don’t have an incentive to provide high quality data. […]

17 Aug 2022

Personalised Incentives and Making our Customers Smile

In AO our philosophy is to put the customer first and always treat them like your Nan, in the Data team we believe this is only possible if you understand who your customers are. We are putting this into practice with the Personalised Incentives project. This aims to tailor the discounts we give to individual […]

17 Aug 2022

Improving product ranges in supermarkets using collaborative topic modelling

In this talk, I’ll show how we can recommend new products to small convenience stores, by leveraging recommendation algorithms similar to those used by Netflix.

17 Aug 2022

Introduction to SQL

Introduction to SQL by Deji Olayinka This will be a simple introduction to the basics of SQL and databases. This includes select statement’s are used to query databases and select the data needed. This includes key syntax like SELECT, FROM , WHERE, LIKE, IN etc.