Giordano Alvari

My name is Giordano Alvari, and I currently work as a Data Scientist at ENEL. In my role, I apply machine learning and deep learning models to a variety of areas, including retail and sustainability. I find this work both challenging and rewarding as it allows me to use my skills in computational biology to extract insights from complex data sets.

In my current position, I have been fortunate enough to work on many exciting projects. For instance, I developed predictive models for energy demand and optimized renewable energy solutions. I am particularly passionate about green tech. It is inspiring to see society's progress toward implementing more sustainable energy solutions, and I am thrilled to contribute to this movement.

Beyond my work, I stay current with the latest developments in the data science community by participating in online forums and attending conferences. I enjoy sharing my knowledge with others and have written articles and given talks on various data science topics.

If you are interested in discussing any of these topics with me or learning more about my background and experience, please do not hesitate to contact me. I am always pleased to connect with fellow data enthusiasts and share my insights and expertise.

I work in the Predictive Machine Learning group, where I design and develop several production-ready machine learning models. 

First and foremost, I collaborated with the Retail and Market Business unit, leading the technical development of churn and claim predictions, scenario-based churn volume forecasting, as well as customer segmentation, and cross-selling for electrification purposes.

Furthermore, I collaborated with various business units, including Enel X, to construct a dashboard for detecting battery anomalies. This tool has proved to be valuable in monitoring and predicting the performance of BESS (Battery Energy Storage Systems).

Moreover, I collaborated on several small projects, including the development of a Bayesian algorithm to simplify document filling and streamline the process. Additionally, I was responsible for maintaining and improving the code for a finder used to optimize the research process of colleagues based on their skills and characteristics.

Besides, I took part in various team activities with the scope of improving the sharing of knowledge and collaboration across the company, such as teaching and recording multiple ML and visualization courses and presenting state-of-the-art tools and papers.

With regard to these projects, I primarily employed Python and Spark pushing for the standardization and deployment of the code based on MLOps best practices and technologies (such as MLflow, Luigi, and Airflow), both on-edge systems and cloud architecture (AWS). Ultimately, I enjoy keeping up with cutting-edge ML models and working on environmental initiatives with a special focus on green energy transition and net zero.

Before joining ENEL, I gained valuable experience in academia working on biological-oriented projects. Some of my notable contributions include:

Benchmarking of single-cell eQTL mapping: In this project, I conducted benchmarking analyses for single-cell eQTL mapping using R and Python. I utilized various tools and libraries such as scikit-learn, PyTorch, and Snakemake. Our findings were published as the first author in the prestigious journal Genome Biology 

Deep networks for cell image analysis: I implemented three different neural network architectures, namely CNN, VGGNet, and CapsuleNet, for classifying a BROAD dataset of cell images based on four different drug clusters. The project was developed using PyTorch, and it focused on accurately categorizing cell images based on the effects of different drugs.

Gene profiling to find putative blood-based Parkinson biomarkers: In this project, I worked with microarray whole-blood data to identify potential Parkinson's disease biomarkers. I employed various approaches such as sPSLDA, Random Forest, LDA, Lasso, and Ridge regression using the R programming language. Our goal was to detect promising biomarkers that could aid in the diagnosis or monitoring of Parkinson's disease.

I hold a Master's degree in Computational Biology, with a focus on machine learning and deep learning applications on biological data. My master's thesis specifically delved into this area, showcasing my expertise in leveraging advanced techniques to extract insights from biological datasets.

Throughout my academic journey, I have been involved in multiple projects where I applied machine learning and deep learning methods to solve complex problems in the biological domain. These experiences have equipped me with a deep understanding of data analysis, model development, and the practical implementation of machine learning algorithms.

In addition to my educational background, I have pursued training in MLOps (Machine Learning Operations), project industrialization, AWS (Amazon Web Services), and project management. This training in project management has enhanced my ability to effectively plan, execute, and oversee projects, ensuring successful outcomes and efficient resource management.

Overall, my education in Computational Biology, experience in applying machine learning and deep learning to biological data, and training in MLOps, AWS, and project management make me a well-rounded candidate with the skills necessary to tackle complex data science projects and drive impactful results.