Skip to main content

FuturePulse: Multimodal Predictive Analytics and Recommendation Services for the Music Industry

Periodic Reporting for period 2 - FuturePulse (FuturePulse: Multimodal Predictive Analytics and Recommendation Services for the Music Industry)

Periodo di rendicontazione: 2018-09-01 al 2020-11-30

The project helps music companies leverage a variety of music data and content, ranging from broadcasters and music streaming data, to sales statistics and streams of music-focused social media interactions and content, through sophisticated analytics and predictive modelling services to make highly informed business decisions, to better understand their audience and the music trends of the future, and ultimately to make music distribution more effective and profitable. FuturePulse offers these capabilities over a user-friendly and visual web solution that enables the immersion of music professionals in the realm of music data and supports them to make highly informed and effective business decisions.
WP1: Open innovation, User Requirements and Design. Main results: 1) Low level co-design of FuturePulse requirements; 2) Delivery of two Music Industry Innovation Reports aimed at position FuturePulse in the highly dynamic landscape of on-line music by continuously analysing the market and pivoting to reach a real value and impact solution across the project lifetime.

WP2: Music Data Collection, Analysis and Indexing. Main results: 1) Data collection (broadcasting, on-line music statistics, social media and open data), which helps the development and evaluation of the predictive analysis and recommendations of artists and tracks in WP3; 2) High-level music content analysis developed and improved; 3) Analysis of the Terms of Service of third parties data sources.

WP3: Predictive Analytics and Recommendations. Main results: 1) Aggregation, estimation and prediction algorithms, a non-linear composite artist popularity score, genre association analysis, listening behaviour and audience and brand profiling; 2) Artist discovery.

WP4: Platform Integration and Application Development. Main results: 1) FuturePulse open platform (https://app.futurepulse.eu/) and API (https://zenodo.org/record/4301354/files/FuturePulse%20APIs%20v1.0.7.pdf). The platform integrated, tested and assessed all the modules researched and developed, and supported the three use cases with a user-friendly, highly intuitive interface of the platform’s capabilities for music professionals.

WP5: Pilots and Evaluation. Main results: 1) Test and evaluation of the FuturePulse platform impact so its outcomes are improved leading to a close-to-market-ready solution; 2) Identification of testers and potential future customers among three key use cases: Record Labels, Live Music and Music Platforms: record label managers, festival bookers, marketers, music editors and DJs, artists, producers, brands, shops, etc. -- were recruited by each WP5 partner or Use Case leader, who set up tests of the platform according to the technical timeline and the available technical features for each phase of the process.

WP6: Innovation Management, Dissemination and Exploitation. The WP focused on the definition of the plans and implementations of the strategies to both reach as many and key agents and partners as possible in music and technology industries, as well as plan individual and joint exploitation of FuturePulse outcomes. All partners were involved in activities related to this WP, involving their expertise and communication tools to achieve the biggest impact possible across all the potential stakeholders, ranging from the general public to specific user groups. As a result, several contacts within the music industry have been established to explore commercialisation paths.

WP7: Project Management. The WP covered the overall management of the project, at the organisational and financial level. Activities included management of amendments, partners’ coordination, quality assurance and risk management, as well as reporting and monitorisation of resources consumption and costs statements. The WP also managed meetings and reports with the External Advisory Board (EAB).

WP8: Ethics requirements. The WP watched for the application of the ethical considerations and requirements included in the deliverables D8.1: POPD – Requirement No. 1 (Protection of Personal Data) and D8.2: H – Requirement No. 2 (Humans): procedures and criteria to identify/recruit research participants, information on the informed consent procedures implemented and clarification whether children and/or adults unable to give informed consent are involved.
Progress beyond the state of the art
Innovate on two problems faced by music industry: a) selection and promotion of music and artists, b) better understanding and engagement of music audience
Actual limitations:
- Fragmented music data are largely fragmented
- Long tail artists, albums and songs and it is missing opportunities to capitalize
- Very little understanding of the underlying preference dynamics, music communities and the particularities in the tastes and trends that arise in different geographies and cultures
- Decisions about the future are based on very simplistic assumptions about how popularity evolves
To overcome these limitations, FuturePulse builds upon advances in a multitude of disciplines, including music/audio analysis and retrieval, data mining and machine learning, psychology and social media analysis.
The FuturePulse project improves upon current state-of-the-art in the two last factors: a) to collect massive amounts of data of various types from various sources; b) to develop new content analysis algorithms that allow using contextual as prior.
FuturePulse moves beyond existing music recommendation systems in two ways: a) It combines contextual factors and groups recommendations to provide businesses with music recommendations that suit their audience b) It measures the impact of music recommendations on business performance indicators.
FuturePulse brings to market a cost-effective and simple-to-use solution for studying the effects of music on the behaviour of consumers in the premises of the business.

Results
The project results in several high-quality outcomes that form the basis for the exploitation plan of the project:
- A robust and extensible multi-source music data ingestion and real-time indexing framework
- A multi-modal music popularity prediction engine
- An online music community analysis framework and a music recommendation engine
- An integrated scalable cloud-based platform offering the full spectrum of FuturePulse services
- A modular market-driven application serving the needs of record labels, event organizers and music platforms.

Potential impacts
FuturePulse will constitute a significant leap of progress in music consumption and distribution, since it is the first project to integrate a number of different signals from both online and physical audiences, with the goals of optimizing music selection and distribution, and creating value for a number of actors in the music ecosystem.
Music convergence technology developed by FuturePulse has the potential of helping European music companies and professionals to capitalize upon the recent trends and disruptions in the creative music industry.
New services to be developed by FuturePulse clearly leverage the convergence of broadband, broadcast and social media.
FuturePulse's platform dashboard
Artist metrics' timeline
Audio analysis of a track
Project Logo
Artists comparison
Impact of events in artist metrics
Artist popularity rankings