Barbara Fusinska

Data Solution Architect

Barbara is a Data Solution Architect with strong software development background. While working with a variety of different companies, she gained experience in building diverse software systems. This experience brought her focus to the Data Science and Big Data field. She believes in the importance of the data and metrics when growing a successful business.

Alongside collaborating around data architectures, Barbara still enjoys programming activities. Currently speaking at conferences in-between working in London. Tweets at @BasiaFusinska and blogs on

Session: Using Machine Learning and Chatbots to handle 1st line technical support

1st line of the technical support is frequently providing answers to FAQ and pre-assembled conversations for operators to follow. With the enhancements in A.I. and Machine Learning, how much of this task could be supported with the aid of software? While this raises many questions and challenges, the first would be how would software understand the intention of the user and hold a human-like conversation.
Based on this particular use case, Barbara will demonstrate how to go from a new project to a chatbot handling technical support. The talk will present the building blocks of the system like receiving and sending messages, natural language processing and integrations with existing messaging platforms such as Telegram, Messenger or Skype.
The session will cover the following topics:
- The existing chatbot ecosystem
- Performing text analysis on user input
- Identifying the best response to the user
- Personalising the response based on who the user is
- Integrating the chatbot into applications and messaging platforms
During this talk, the audience will gain knowledge of the components necessary to build chatbot based system, including natural language processing and messages handling. The aim is that attendees will be able to go from never writing a chatbot, to building one which is capable of holding a conversation.

Workshop: Machine Learning with Azure

Modern companies do realise how making use of their data can enhance the business. But building the Data Science team requires either hiring the skilled staff or putting a lot of effort into internal education. This is the place when Azure Machine Learning Studio comes in. It offers low-cost, easy to use and managed environment. The Studio provides educational space making entering the field of Machine Learning more accessible. 
The workshop is a comprehensive introduction to the various Machine Learning concepts and is covering the following topics:
- Creating the Azure Machine Learning experiments
- Importing data from Azure sources and working with datasets
- Data cleaning and manipulation
- Exploratory Data Analysis
- Performing the training for supervised and unsupervised Machine Learning tasks 
- Tuning the Machine Learning models
- Customising the process by using R and Python code
- Working with Jupyter notebooks in the Azure ML workspace
- Publishing and consuming a Machine Learning web service for predictive analysis
- Retraining the Machine Learning model
The workshop will walk the attendees through the Machine Learning process, how to build one in Azure ML Studio and publish the predictive experiment. With the enhancement of the R and Python code, participants will have the opportunity to customise the flow. Finally, the session will provide the ways of productionising the built solution by publishing it to Azure.


Price for workshop: DKK 6.900 (ex.VAT)

Price for workshop and conference: DKK 7.300 (ex.VAT)