Javier Sanz-Cruzado

Do you want to know more? Read our pre-print: javiersanzcruza.github.io/assets/paper... (5/5)

Experimental results showing that transaction-based metrics are negatively correlated with profitability-based metrics in our experiments, and the reasons why: 1. Customers are not necessarily good investors. 2. Customer skill varies over time. 3. Customer strategy might change performance of models.

Through our theoretical and empirical analysis, we find that customer transactions are a problematic source of data for evaluation on their own, and they might lead customers to lose money if they are not good investors. 🧵(4/5)

Example of evaluation of financial asset recommendations.

1. Transaction-based evaluation measures if FAR methods can predict future customer investments. It relies on IR/RecSys metrics like nDCG.
2. Profitability-based evaluation estimates if customers would earn money by following the recommendations. Example metric: ROI 🧵(3/5)

Introduction figure to financial asset recommendation.

In this paper, we focus on the problem of financial asset recommendation (FAR), i.e., identifying stocks, bonds or mutual funds on which a customer might invest. In particular, we compare two of the most common ways of evaluating models for this task 🧵(2/5)

Title and authors of the paper.

Paper alert 🚨"Investors Are (Not) Always Right: A Comparison of Transaction-Based and Profitability-Based Metrics for Financial Asset Recommendations", with @richardmcc.bsky.social, Nikos Droukas, @craigmacdonald.bsky.social & @iadhounis.bsky.social has been accepted at ACM TOIS! 🧵(1/5)

Biomedical text mining for knowledge extraction @ ISMB 2025 A hands-on tutorial introducing biomedical natural language processing including named entity recognition, relation extraction and the power and limits of large language models.

Had fun talking about biomedical information extraction with @javiersanzcruza.bsky.social today. Check out the materials from our #ISMBECCB2025 virtual tutorial. It's a mini intro course on #BioNLP! ai4biomed.org/ismb2025tuto...

Very happy to announce that our paper "Accelerating Cross-Encoders in Biomedical Entity Linking" with @jakelever.bsky.social has been accepted to the #BioNLP2025 workshop!

Congratulations to @tjaenich.bsky.social who defended his PhD Thesis Fair Group-Based Exposure of Documents in Ranked Search Results 👏👏

Was a pleasure supervising your PhD along with @iadhounis.bsky.social. @irglasgow.bsky.social

Thanks to the examiners Dr. Sole Pera and Christos Anagnostopoulos!

An amazing work by @ttsamurai.bsky.social! Happy to see so much interest on conversational financial agents from the #ECIR2025 community!

A large contingent of our staff & students @uofgcompsci.bsky.social will soon be traveling to #ECIR2025. We'll be presenting our latest work in #search & #RecSys throughout the 5-day conference.

Looking forward to connecting with colleagues and friends in Lucca!

Happy to share that our paper "Improving novelty and diversity of nearest-neighbors recommendation by exploiting dissimilarities" with @psperez.bsky.social and @abellogin.bsky.social has been accepted to #ECIR2025 IR4Good track!

Demo paper entitled “FinPersona: An LLM-Driven Conversational Agent for Personalized Financial Advising” has been accepted to #ecir2025 - output of a collaboration with University of Tokyo with T Takayanagi, M Suzuki, K Izumi, R McCreadie, @javiersanzcruza.bsky.social and @iadhounis.bsky.social

🙋

You can find more information about my research and publications on my personal website: javiersanzcruza.github.io

Happy to be here!

4. As a post-doc, I also worked in several projects related to recommender systems and machine learning applied to the financial domain, with (among others) @richardmcc.bsky.social , @iadhounis.bsky.social and @craigmacdonald.bsky.social .

3. I obtained my PhD in Computer Science at the IR Group at Universidad Autónoma de Madrid 🇪🇸, working on people recommendation in social networks.

2. I am currently working on NLP with @jakelever.bsky.social , exploring how to extract useful information from biomedical research papers to facilitate the creation of cancer-related knowledge-bases.

Considering this is a new social network, I will take the opportunity to introduce myself to the research community here.

1. I am a post-doctoral researcher at the Information Retrieval Group at the University of Glasgow 🏴󠁧󠁢󠁳󠁣󠁴󠁿(@irglasgow.bsky.social), interested in RecSys, graphs, IR and NLP.

Hello everyone! Happy to be here! If you are interested on the research that we do at @irglasgow.bsky.social (IR, RecSys, NLP), I have created an starter pack for you!

Access it here: go.bsky.app/BM6iHbU

I will keep updating it over time as more people in our team join BlueSky!