real-world modelling of socio-technical systems

Predicting the success of start-ups: a network science approach

Summary of the research:
By drawing on large-scale online data we are able to construct and analyze the time-varying worldwide network of professional relationships among start-ups. The nodes of this network represent companies, while the links model the flow of employees and the associated transfer of know-how across companies. We use network centrality measures to assess, at an early stage, the likelihood of the long-term positive economic performance of a start-up. We find that the start-up network has predictive power and that by using network centrality we can provide valuable recommendations, sometimes doubling the current state of the art performance of venture capital funds. Our network-based approach supports the theory that the position of a start-up within its ecosystem is relevant for its future success, while at the same time it offers an effective complement to the labour-intensive screening processes of venture capital firms. Our results can also enable policy-makers and entrepreneurs to conduct a more objective assessment of the long-term potentials of innovation ecosystems, and to target their interventions accordingly.

Predicting success in the worldwide start-up network

Moreno Bonaventura, Valerio Ciotti, Pietro Panzarasa, Silvia Liverani, Lucas Lacasa, Vito Latora

NPG Scientific Reports 10, 345 ( 2020) Featured in AAAS , phys.org ,wired , 7th space ,QMUL

Predicting success in show business

Summary of the research:
In certain artistic endeavours—such as acting in films and TV, where unemployment rates hover at around 90%—sustained productivity (simply making a living) is probably a better proxy for quantifying success than high impact. Drawing on a worldwide database, here we study the temporal profiles of activity of actors and actresses. We show that the dynamics of job assignment is well described by a “rich-get-richer” mechanism and we find that, while the percentage of a career spent active is unpredictable, such activity is clustered. Moreover, productivity tends to be higher towards the beginning of a career and there are signals preceding the most productive year. Accordingly, we propose a machine learning method which predicts with 85% accuracy whether this “annus mirabilis” has passed, or if better days are still to come. We analyse actors and actresses separately, also providing compelling evidence of gender bias in show business.

Papers:

Quantifying and predicting success in show business Oliver Williams, Lucas Lacasa, Vito Latora
Nature Communications 10, 2256 (2019)
Research highlighted and featured in over 100 different media including:

Nature Eurekalert (AAAS) The Guardian El Pais The Times El Periodico phys.org Agencia SINC Discover The Telegraph Natureasia Mail Online cosmosmagazine Science Daily El Espectador zmescience El Colombiano La Sexta World News Buz La Jornada Cultura Inquieta QMUL

Silver-screen or starving? Predicting success in showbiz

Oliver E. Williams, Lucas Lacasa TheScienceBreaker (2019)

Predicting online conversion in e-commerce

Summary of the Research:
To make a long story short, a team of researchers from across academia and Coveo extensively tested the hypothesis that it is possible to detect user intent based on click-stream data. More specifically, we wanted to find the answer to the following question: If I record every click on a target Ecommerce website, after how many clicks am I able to reliably predict if the user is a buyer or just a window shopper?

More academical summary:
We address the problem of user intent prediction from clickstream data of an e‑commerce website via two conceptually different approaches: a hand‑crafted feature‑based classification and a deep learning‑based classification. In both approaches, we deliberately coarse‑grain a new clickstream proprietary dataset to produce symbolic trajectories with minimal information. Then, we tackle the problem of trajectory classification of arbitrary length and ultimately, early prediction of limited‑length trajectories, both for balanced and unbalanced datasets. Our analysis shows that k‑gram statistics with visibility graph motifs produce fast and accurate classifications, highlighting that purchase prediction is reliable even for extremely short observation windows. In the deep learning case, we benchmarked previous state‑of‑the‑art (SOTA) models on the new dataset, and improved classification accuracy over SOTA performances with our proposed LSTM architecture. We conclude with an in‑depth error analysis and a careful evaluation of the pros and cons of the two approaches when applied to realistic industry use cases.

Paper:

Shopper intent prediction from clickstream e-commerce data with minimal browsing information

Borja Requena, Giovanni Cassani, Jacopo Tagliabue, Ciro Greco, Lucas Lacasa

Scientific Reports 10, 16983 (2020)

Featured in COVEO blog

Quantitative methods for electoral fraud detection