Suggestions
Michele Caputo
Data Scientist
Michele Caputo is a Data Engineer/Scientist at the European Securities and Markets Authority (ESMA). He specializes in data science and big data applications, contributing to the organization's efforts in financial regulation and oversight. His work involves analyzing complex datasets to support decision-making processes within the financial markets.
Professional Background
- Current Role: Data Engineer/Scientist at ESMA
- Expertise: Data analysis, machine learning, and financial data management.
Contributions
Michele is active on platforms like LinkedIn, where he shares insights related to data science and its applications in finance. His professional activities suggest a focus on enhancing data-driven strategies within regulatory frameworks.
Academic Involvement
Michele has also contributed to academic literature, including topics related to wave propagation in materials, indicating a strong background in both theoretical and applied sciences.12
For more detailed insights into his professional journey and contributions, you can view his LinkedIn profile under the username michelecaputo83.
Highlights
And finally the big day came. Two years of big sacrifices - and big satisfactions - converged in the graduation day of my Executive Master in Statistics and Big Data at the Paris Dauphine University - PSL. A journey that would have been impossible without the unconditional love and support of a fantastic wife and two splendid children.
What now? I'm continuing on my path as a Data Scientist on a very solid ground, built thanks to the excellent education I received. An education that taught me what's "under the hood" of Data Science concepts, algorithms, techniques and tools, opposed to a "black box" approach. A perfect match for me, a person curious by nature who loves deep knowledge, always longing for "a-ah!" moments - those who know me recognise the child inside me when something is not a mystery anymore. There will be hurdles, it won't be easy, but that's part of the game. The fun begins now.
--
Enfin, le grand jour est arrivé. Le terminus de deux ans de grands sacrifices - et grandes satisfactions – était la cérémonie de remise des diplômes du Executive Master en Statististique et Big Data à l’université Paris Dauphine – PSL. Un voyage que je n’aurai pu faire sans l’amour et le support inconditionnels de ma femme et de mes enfants.
Et maintenant ? Je continue mon parcours de Data Scientist sur des bases très solides, construites grâce à l’excellente éducation reçue, qui m’a appris ce qu’il y a derrière les concepts, les algorithmes les techniques et les outils de la data science, au lieu de les traiter comme une boite noire. Ce qui est dans ma nature, j’ai une inclination naturelle vers la connaissance profonde, je suis toujours à la recherche de ces moments où je dis "a-ah !" - ceux qui me connaissent reconnaissent l’enfant en moi quand quelque chose n’a plus de secrets pour moi.
Il y aura des obstacles, il ne sera pas facile, mais ces sont les règles du jeu. Le divertissement commence.
#datascience #bigdata #education #statistics
Anomalies can be the unwanted guest when modelling or their very same detection may represent the ultimate goal of a project.
Either way, their identification is crucial in any data science workflow that has to deal with real data. As in real life project, many questions may arise:
- which algorithm for outlier detection should be used?
- how should its parameters be tuned?
- how to track the results of one's research?
- how to put all of these aspects together?
These were all questions that Milos Colic, Iliya Kostov and I wanted to answer to with #kakapo. Kakapo builds on top of #pyod for having a vast library of anomaly detection algorithms at one's fingerprints, #mlflow for model tracking and serving and #hyperopt for distributed hyper-parameters tuning. All of this, at scale, on #databricks. We hope you'll enjoy using kakapo!
#data #datascience #kakapo #outlierdetection #anomalydetection
