Game Data Science: The State of the Art
In the last few years, we have witnessed a true revolution in the video-game industry, as both traditional video-game platforms and emerging mobile games have become always connected to the Internet. This has contributed to widen the audience for video games (casual gamers) and to the appearance of new economic models (in-app purchases, free-to-play) that are gaining more and more importance in a sector traditionally monetized by expensive one-time purchases or subscriptions.More importantly, this recent paradigm shift allows game developers to collect a huge amount of data in real time while maintaining an active relationship with the players. This has created a broad range of new challenges and opportunities for both data science research and business applications, as demonstrated by the quickly growing number of job openings for data scientists in game companies. To fully take advantage of this new scenario, it is paramount to develop adequate statistical and learning methods that model and predict player behavior, scale to large datasets and allow an intuitive visualization of the results.
In this talk, I will survey the state-of-the-art of Data Science in the mobile game industry. First, I will present a general summary of the main techniques to predict player behavior, concentrating on those learning methods that help to reduce user attrition, i.e. churn, which is decisive to increase player retention and raise revenues.
Then, I will discuss these techniques from the viewpoint of Game Data Science as a Service. The goal of Silicon Studio is to democratize Game Data Science. Hence, I will show how the proposed methods can make predictions in an operational business environment and easily adapt to different kinds of games and players—namely, to different data distributions. I will focus on flexible techniques that do not need previous manipulation of the data and are able to deal efficiently with the temporal dimension of the churn-prediction problem.
Big Data - 'Nuclear Weapon' in Shared Economy Era
With case studies of Mobike, the presentation of Zhen Wei will cover the following areas:- Shared bike's past and present- Shared city is a smart city- IoT must be followed with Big Data
Driving Corporate Decision - Making with Data Analytics
Abstract coming soon.
Upgrading Traditional Industries with New Technologies
With the experience building up a world class BlockChain CoE with 50+ experts, ranging from finance, cryptography, digital currency, p2p to distributed computing etc, landing massive use cases that will disrupt commercial banking, healthcare and supply chain etc, Charles is now one of the members leading the block chain development in China.After the development of Blockchain Technology in China in the last two years, there have been successful projects launched not only to improve the business performance but also to bring better social impacts. Charles will share some of the projects he has been involved in with the an outlook of blockchain.
Challenges of Digitalization in Retail Industry
Eddie will introduce the digitalisation in retail industry and some traps as well as challenges along the journey.
Chinese Consumer Perception of a Brand through Sentiment Analysis
China market is rapidly increasing. Yet, companies have hard time in following the market trend and understand 1.3B consumer thoughts due to unmeasurable data sources.
In this session, we try to capture the importance on understanding different types of consumer voices and their sentiment behind them. This is done by gathering all the vast amount of scattered data through conversation between consumers, brands engagements, consumer reviews, and etc.
Through deep learning, it is now possible to measure and listen to what consumer really perceive; with the most accurate, and customized data.
Lunch @ Exhibition Foyer
How Airbnb Use Data to Make Decisions at Scale
This presentation will cover the following areas including:- Airbnb is a data-informed company- Experimentation in Airbnb- Data Products in Airbnb- Scaling data usage
Workshop: Application of Knowledge Graph in the Big Data Era
Since Google launched the first version of its knowledge graph (KG) in 2012, the research area of KG has been attracting a lot of attention from both academia and industry. Major internet companies in China also followed up, and gradually applied KG to their respective systems.
Initially, KG was applied in the field of information retrieval, which enhanced the search experience, such as searching for a celebrity with the return of their social relations, previous achievements, relate persons along with normal search results. With the driving of big data, the scale of KG is exploding, and the application field is expanding more widely, such as network analysis, anti-fraud, precision marketing, among many others.
Through the extraction of entities and relationships, we have embedded the prior knowledge to KG in the constructing process. However, there are some implied inter-entity relationships that are missing. Only after careful reasoning will they appear. This leads us to an important area of the KG: knowledge inference.
In this talk I will discuss how Alibaba has successfully applied KG technology to increase the values of the data in the era of big data.
Towards the Future of Artificial Intelligence
Janusz will use some research results and implications to provide audience with an insight on the development of Artificial Intelligence from its origin to current applications and to the future.
Insights Sharing: The Past, Present and Future of Big Data
The importance of data has been realised by more and more companies. It changed the way how traditional companies are performing from product management to operations.The CTO of Analysys and the big data director of E Le Me (饿了么) will share some insights from their tens of years' experiences with real case studies on how IOTs & AI are implemented to bring evolutionary changes in real businesses.
Registration & Light Breakfast
China Data Cross-border Transmission Compliance Requirements Introduction
Cross-border data security is a big challenge for multi-national companies. As the CISO of Philips China, Roy will share his experience on how to overcome these challenges and how to manage data security in various regions.
Driving Physical Store Productivity through Big Data Analytics
Ray will share a project implemented by Adidas to improve the physical store performance across China. This will cover what data can be used for insightful analysis and how the analytics can be used for further actions.
ZF World Class Manufacturing with Industry 4.0 IoT and Artificial Intelligence
Esteban will share his experience on leading ZF's Digitalisation Strategy. The experiences will cover the best practices ZF group has achieved on Industry 4.0, Machine Learning and Artificial Intelligence for the Automotive Industry.
The Technology Nature of Blockchain - Disruption, Independence & Innovation
Ping will introduce what blockchain is, why it is a disruptive technology and what innovation it brings in terms of implementations.
The Implementation of Robo-Advisor
Robo-advisor is becoming a very hot topic now Finance industry. Dong Xiaojian will introduce the development journey of robo-advisor in Tong Ban Jie.
Fireside Chat: Big Data for Marketing Campaigns
With tens of years experience on digitalisation and data-driven marketing, James will share how big data is changing marketing to achieve better RoI for businesses.
Lunch @ Exhibition Foyer
Workshop: Trends and Application for Deep Reinforcement Learning
In this talk, Janusz will share based on a research project he has been focusing on in the last few years, which is the "Artificial Brain Cognition". The main objective of this research has been to develop a computing model mimicking a biological brain, with three key features: structural equivalence, task equivalence and computational equivalence. He will also share some applications of Deep Reinforcement Learning across the world at the moment.
Data Science Drives Risk Management of FinTech Industry
In this presentation, Shanren will introduce the challenges of the finance industry on risk management. He will also bring the case studies of Yi Ren Dai on how they mitigate the risks in the long term by using the platform of Feng Chao.
Panel Discussion: Big Data for Better Marketing Performance
The panel discussion will bring up the insights on how big data analysis can be used to evaluate the marketing effects better, what data can be used to analyse the feature of Innovations, and the use of data analysis in different marketing scenarios.The discussion will be led by the COO of Umeng+, CMO of Variflight (飞常准), CEO of Kuyun(酷云) and CEO of Marketin.