PyData London - 47th Meetup

NOTE: A valid photo ID is required by building security. Please use your full real names when signing up, otherwise you may be refused entry!

---

There'll be free food & drinks, generously provided by our host, AHL.

We are issuing tickets via a lottery - if you want to be in with a chance of a place - sign up for the waitlist! The lottery will be run approx 1 week before the meetup, and we will re-run the lottery to fill any spaces that free up or use the waitlist towards the time of the event.

Main Talks:

• Dinesh Vadhia on "Popping your Filter Bubble"
  Conventional recommendation services like Netflix, News Feeds, Spotify and in commerce trap you in a filter bubble. A watched movie continues to be suggested; new items do not appear immediately; you cannot interact with the results to improve personal relevance; data security and privacy is abused. The AI has all the control leaving you open to behavioural manipulation.

Thingy pops the bubble to give people control of their AI.

The work, in collaboration with Professor Zoubin Ghahramani (http://mlg.eng.cam.ac.uk/zoubin/) at Cambridge University, is show-cased in 3 articles with must-see results using images:
https://medium.com/@DineshVadhia/realtime-ai-is-no-longer-a-myth-9d43dc55342f https://medium.com/@DineshVadhia/interactive-ai-with-tom-cruise-977e1b128def
https://medium.com/@DineshVadhia/the-end-of-dumb-ai-c4c021b9a132

The talk will walk through why Thingy solves the problems of conventional recommendation engines and show example results.

• Marc Garcia on "Towards pandas 1.0"
  It's been 10 years since pandas development started. In this time, pandas growth in popularity has been incredible, becoming the de-facto standard for data analysis, to the point of being responsible for 1% of StackOverflow traffic. And the development of pandas continues strong, with new features and many fixes coming at every release.

In this talk we'll start with the motivation for the project. Covering its past, the current development and latest features, and what can we expect from the project in the future.

Marc (https://twitter.com/datapythonista) is a pandas core developer and Python fellow. His academic background is in AI and finance. Having worked with Python for the last 12 years, and in the data field for the last 5. He's the organiser of the London Python sprints group, and a regular speaker at PyData and PyCon conferences.

Lightning Talks:

King Wong on "Forecasting Structural Breaks in Application to Algorithmic Trading"

Undesirable market crashes happen often especially in new securities such as cryptocurrency. Here I tried to apply Hidden Markov Model to predict market crashes in conjunction to design and to backtest a simple trading strategy. I will present the results of the strategy, the mistakes I made in the models and possible improvements for further development.

Pushkal Agarwal on "How Do People Engage Online With Parliamentary Debates?"

We employ Non-Negative Matrix Factorization (NMF) and Principle Component Analysis (PCA) on the video views (6 Million in last 2 years) matrix to identify different archetypes of users, and identify 3 archetypes (Direct, Social and Search). Interestingly, these different archetypes appear to have different levels of engagement with the Parliamentary videos. Hence we define the properties like view length, topics interested, the device used and so forth for each of them.

Logistics:

Doors open at 6.30pm (get there early as you have to sign-in via AHL's security), talks start at 7 pm, drinks from 9 pm in the bar. We normally have >200 folks in the room so there's plenty of people to discuss data science questions with!

Please unRSVP in good time if you realise you can't make it. We're limited by building security on the number of attendees, so please free up your place for your fellow community members!

Follow @pydatalondon (https://twitter.com/pydatalondon) for updates and early announcements. See you on the 14th!