Buliding text based data products in the real world & smart buildings

Data Science Melbourne
Data Science Melbourne
Public group

Location visible to members


The talks will start around 6pm

Feel free to arrive from 5:15 and grab a beer and pizza.

The door to the basement is actually on Queen St, just a few meters down from the corner of Queen and Collins. Please enter via this door.

Lukas Toma: "Buliding text based data products in the real world"

About the Talk: The talk will explore the factors that drive the decisions for selecting the right machine learning technique for data products at a SaaS company. We will go through practical examples from text-based data products to understand the constraints that influence your choices. The examples will be based on Prezly solutions for 'Related Stories', 'Influencer Matching' and 'Topic classification' products. Lukas will outline the intuition behind a range of methods and describe how they behave under product constraints.

About the Speaker: Lukas currently works as Lead Data Scientist at Prezly (http://www.prezly.com/), a SaaS company building software for people working in external communications and public relations. He is also a co-founder ofdata-consulting company Knoyd (http://www.knoyd.com/) and co-founder at data science bootcamp called Basecamp.ai (http://basecamp.ai/). He was previously an early employee at Austrian travel start-up Ulmon (http://www.ulmon.com/) and 700mil. EUR German fin-tech start-upKreditech (http://kreditech.com/).

Cameron Roach:"Intelligent Buildings"

About the Talk: Building Management Systems (BMSs) are used to control HVAC equipment, lighting and other devices in commercial buildings. These systems can generate significant volumes of data with a single building typically containing tens of thousands of sensors. Buildings Alive are focused on collecting and using this data to help facilities managers and service engineers make better decisions to reduce energy consumption. This talk focuses on various data science techniques we are using to better analyse data collected from BMS devices and sensors. An overview of the data as well as an introduction to producing an analytics dashboard using python's recently released Dash framework will be included.

About the Speaker: Cameron Roach is currently completing his PhD in econometrics and business statistics at Monash University while working with Buildings Alive. He previously completed a Master of Science at The University of Melbourne majoring in probability and statistics and has worked in several industries including energy forecasting and environmental consulting. He is the author of several open source R packages including validatr and myhelpr.