Science / Press

A. Farseev and T.-S. Chua. Tweet can be Fit: Integrating Data from Wearable Sensors and Multiple Social Networks for Wellness Profile Learning ACM Transactions on Information Systems (TOIS), 2017. 17 January 2019

Wellness is a widely popular concept that is commonly applied to fitness and self-help products or services. Inference of personal wellness-related attributes, such as Body Mass Index (BMI) category or diseases tendency, as well as understanding of global dependencies between wellness attributes and users’ behavior is of crucial importance to various applications in personal and public wellness domains. At the same time, the emergence of social media platforms and wearable sensors makes it feasible to perform wellness profiling for users from multiple perspectives. However, research efforts on wellness profiling and integration of social media and sensor data are relatively sparse, and this study represents one of the first attempts in this direction. Specifically, we infer personal wellness attributes by utilizing our proposed multi-source multitask wellness profile learning framework — “WellMTL”, which can handle data incompleteness and perform wellness attributes inference from sensor and social media data simultaneously. To gain insights into the data at a global level, we also examine correlations between first-order data representations and personal wellness attributes. Our experimental results show that the integration of sensor data and multiple social media sources can substantially boost the performance of individual wellness profiling.

A. Farseev, I. Samborskii, A. Filchenkov, and T.-S. Chua. Cross-Domain Recommendation via Clustering on Multi-Layer Graphs 40th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR'17), August 7-11, 2017. 17 January 2019

Venue category recommendation is an essential application for the tourism and advertisement industries, wherein it may suggest attractive localities within close proximity to users’ current location. Considering that many adults use more than three social networks simultaneously, it is reasonable to leverage on this rapidly growing multi-source social media data to boost venue recommendation performance. Another approach to achieve higher recommendation results is to utilize group knowledge, which is able to diversify recommendation output. Taking into account these two aspects, we introduce a novel cross-network collaborative recommendation framework C 3R, which utilizes both individual and group knowledge, while being trained on data from multiple social media sources. Group knowledge is derived based on new crosssource user community detection approach, which utilizes both inter-source relationship and the ability of sources to complement each other. To fully utilize multi-source multi-view data, we process user-generated content by employing state-of-the-art text, image, and location processing techniques. Our experimental results demonstrate the superiority of our multi-source framework over state-of-the-art baselines and different data source combinations. In addition, we suggest a new approach for automatic construction of inter-network relationship graph based on the data, which eliminates the necessity of having pre-defined domain knowledge

Press About Us

Investible - Investment Notes: SoMin.ai 17 August 2022

A look inside Investible's backing of SoMin.ai, a startup revolutionising the digital marketing industry.

Earlier this year, Investible backed Singapore-based SoMin.ai, a deep-tech marketing technology that leverages machine learning to give marketers a better return on their advertising spend investment. The business is led by co-founders Aleksandr Farseev (CEO) and Kirill Lepikhin (CTO), a technical and incredibly savvy duo intimately familiar with the sector they have begun to disrupt.

Traditional marketing approaches are not cost-efficient. It can be difficult for marketers to correlate the money spent on a marketing campaign with revenue from sales (i.e. return on marketing spend). Currently, one way to measure and test advertising campaigns is iterative A/B testing through focus groups. With the introduction of machine learning and natural language processing, there are now ways to derive insights that reflect the wider market and not just select sample sizes. Big data algorithms now have the capability to scrape data from user-generated content (e.g. what consumers have liked on Instagram) and use it to create an intimate understanding of consumer behaviour.