Rationence at the next conference SAS Innovate 2025

Rationence will participate as winner of the international competition SAS Hackathon 2024 in the Life Sciences category

The SAS Innovate conference takes place in Orlando (Florida).
the SAS Innovate conference

Link to the SAS Innovate conference

During the conference, the final Hackathon 2024 winner will be voted among the winners of all the categories, including the Rationence Team with our solution Abstract Finder. The Abstract Finder project uses generative artificial intelligence to improve searches in the biomedical literature. Powered by the cloud-native Sas Viya platform, the solution enables researchers, students and medical professionals to quickly find the abstracts they need in the PubMed database, accelerating scientific discovery.

Some web magazines speaking about our partecipation:

Link to the Bitmat web magazine "Il team di Rationence, azienda italiana di consulenza IT e partner di SAS, ha sviluppato Abstract Finder, una soluzione che sfrutta l’intelligenza artificiale generativa per migliorare il reperimento della letteratura biomedica. Alimentata da SAS Viya, la soluzione aiuta i ricercatori, i professionisti del settore medico e sanitario e gli studenti a trovare rapidamente gli abstract di cui hanno bisogno all’interno del database PubMed per far progredire la scoperta scientifica."

Link to the Business People web magazine "Tra i vincitori di quest’anno spicca l’italiana Rationence, che ha conquistato il premio nella categoria Global Industry Winners, Life Sciences grazie al progetto Abstract Finder. Il progetto Abstract Finder utilizza l’intelligenza artificiale generativa per migliorare la ricerca nella letteratura biomedica. Alimentata dalla piattaforma cloud-native Sas Viya, la soluzione consente a ricercatori, studenti e professionisti del settore medico di trovare rapidamente gli abstract necessari nel database PubMed, accelerando la scoperta scientifica."

Python and SQL ChatBot!

More and more in demand, chat bots are now able to translate your data analysis prompt into Python and SQL code, and then applying them to provide insight, code, export data, and draw charts!

Here below, we are showing some custom chatbot solutions that demonstrate our ability to develop web apps that starting from data analysis requests in a natural language of your choice are able to interpret your prompt and execute programs on your data without coding any statement.
They are under continuous development to improve their funcionalities. The versions here illustrated are currently available in Italian and English languages. Demo and screenshots were built at the state of the art in date 14th April 2025.

These solutions can provide you:

1. a column description and a table preview of the data loaded or available in a schema of your database.
2. a chat interface in any natural language, being able to translate user requests into queries and actions, automaticaly submitted and executed on the database.
3. a program in SQL or Python code corresponding to your request to be executed or submitted.
4. an explanation of the steps to produce the code above.
5. the results of the execution or submission of the code starting from your data and database.
6. an optional extraction of your data as requested to be exported into CSV or Excel files.
7. some optional charts as requested to describe your data.
8. functions and statistics such as correlation can be provided too.

These ChatBots are written in python and do not require any specific software license.
By default, an API KEY is required to access an LLM model such as those provided by Open AI.
However, alternative open source LLM Models can be implemented on a local private server to avoid any costs, and to prevent any even small amounts of information from being collected by providers such as Open AI.

Looking at the demos shown in the videos below, you can observe that these ChatBots are quite intelligent in interpreting your requests starting from prompts of few words, even just a line.
Finally, they automatically detect all the keys that link the available tables, and they are able to join or merge multiple tables without any user's hints or external metadata, as to code subqueries by themselves.

Below you can find a short video of our chatbot demo named "Chattino", version Python coding.

Download English version of the video(about 32 MB)

Download Italian version of the video(about 39 MB)

Below you can find a short video of our chatbot demo named "Chattino", version SQL coding.
We apologize for the video being available only in Italian.

Download Italian version of the video(about 30 MB)

CV Ranking with Large Language Models

A smart solution to support the HR function in scouting the right candidates among a large set of CVs

Currently, personnel selection processes require significant amounts of time and effort, especially for companies managing multiple open positions simultaneously or receiving large quantities of CVs after posting a job offer.
CV-Ranking is a smart solution based on LLM models to support the HR function in scouting CVs, in order to find the most suitable ones for the required position. The system takes as input a natural language job description and a large set of resumes as input, and then provides a ranking of the most suitable CVs for the entered job description, speeding up the CV selection process.

CV acquisition module takes PDF formatted CVs as input and extracts the textual part, making the documents processable. Then a pre-processing phase follows, which aims to clean and process the textual data previously extracted from the CVs, through Lemmatization, N-grams and Bi-grams creations, stop words removal and so on.


Based on the results of the aforementioned phases, a word embedding process is carried out, which is a technique that allows storing both semantic and syntactic information of words starting from an unannotated corpus and building a vector space where word vectors are closer if the words occur in the same linguistic contexts, meaning they are recognized as semantically similar. The vectors resulting from this process are inserted into a knowledge base, preserving the metadata, in order to subsequently trace back from the vectors to the CVs that originated them.


Then follows a Job Description analysis module, whose purpose is to extract skills from the Job Description entered by the user in any natural language to be searched among the CVs. The extraction is performed by providing the relevant text to a Large Language Model (LLM) accompanied by an appropriate prompt.

The vectors generated by the word embedding of CVs and the skills extracted from the job description are then crossed, evaluating their similarity, under the assumption that, due to the functioning of the applied word embedding procedure, numerically similar vectors represent texts similar in meaning.

At this point, for each document in the knowledge base are associated N similarity scores, where N is the number of skills of interest. These N scores are then summarized into a single score through a weighted sum, which serves as a model to provide an overall ranking related to all skills, constituting the system's output.

The current CV-Ranking interface allows the user to customize some of the previously illustrated phases according to their needs. By the way, Large Language Models might have "hallucinations", meaning it might provide inconsistent outputs. The remedy devised for this intrinsic and unpredictable possibility is to provide a feature that allows users to select and remove any undesired skills via a dropdown menu based on their needs.

Not all skills extracted from a Job Description might hold equal importance for a user. Therefore, a functionality was incorporated into the interface to enable the selection of skills deemed strictly necessary for the desired candidate.

Once these specifics are entered, it is then possible to trigger the analysis by pressing a button and obtain the result, consisting of a table in descending order showing the top ten CVs most suitable for the entered Job Description, along with their respective scores and the option to view the CVs of individual candidates.
Simultaneously with the tabular output, the user is presented with graphs that allow visualization and comparison of the details of the scores generated on the top CVs for each individual skill used in the search.

The system has been tested with more than 2500 CVs, providing results in just a minute.

Rationence Ten Years Anniversary

"In January 2025 Rationence celebrated 10 years of presence on the market."

On Monday, January 21, 2025, Rationence celebrated 10 years of presence on the market. The anniversary was then celebrated in the prestigious restaurant of Villa Torretta.
We hope for another 10 anniversaries of this kind!

SAS-TD-SYNNEX Channel Event

"Accellerare il Business con SAS e TD SYNNEX: Strategia, Tecnologia e Partnership per il Futuro."

On Tuesday, February 4, 2025, during a partner event organized by SAS in collaboration with TD Synnex in Milan, Rationence presented its solution "Abstract Finder" with which it won the recent global SAS Hackathon competition in the Life Sciences category.
We thank SAS for the opportunity to present our solution.

Radio interview with the president of Rationence

Radio interview with our president Giuseppe Marcon for StoryTime on Radio Canale Italia on 12-18-2024.
A personal insight of his career and some of the values that guided to the born of Rationence.

- The interview on our YouTube channel!

SAS Hackathon 2024
Awards Ceremony
Ratio Team Winner
(YouTube link)

Rationence Winner
at SAS Hackathon 2024!

We won the SAS international competition in the Life Sciences category!

We are proud to announce our winning at the SAS Hackathon 2024 competition in the Life Science category. During the period of the competition, our team implemented an innovative solution to search, summarize and rank scientific articles from the famous PubMed central database.
The solution exploits the capabilities of generative AI to enhance Biomedical Literature Retrieval and it integrates several innovative technologies such as:

1. a chat interface in natural language that is able to translate the request of the user into PubMed queries taking advantages from the modern Artificial Intelligent platforms. The queries are automatically submitted to the database.
2. a text mining system to evaluate and summarize the found articles into short abstracts.
3. a web user friendly interface to browse the ranked articles with direct access to their documents in PubMed.
4. a set of analytical dashboards to explore the search activities and the quality of the results.

The solution integrates a serie of Python libraries with several SAS products of the Viya suite, including SAS Visual Analytics and SAS Visual Text Analytics.

Below you can find the short version of our presentation at the Hackathon competition and a link to a longer and technical video presentation.

Download long technical version of our presentation(about 380 MB)

Our version of these videos published on our YouTube channel!

- Rationence Winner at SAS Hackathon!

- Rationence Winner at SAS Hackathon! (Long Version)

Master BI&BDA!

Master in Business Intelligence and Big Data Analysis!

For the second consecutive year, Rationence is sponsor of the master's degree in Business Intelligence and Big Data Analysis that is regularly kept by the University of Milan Bicocca, (Address: Via Bicocca degli Arcimboldi, 8.)

Master BI&BDA

Credit Risk Case Study proceeds!

The Case Study based on a Credit Risk sample data set has been fully documented in R language, using Knime software, and in Python!

1. R-Shiny


2. Knime


3. Python


4. Microstrategy (ongoing)


5. SAS (ongoing)

We are going to finish the documentation of the Microstrategy project development of the same case study. Final step the presentation of a solution with SAS Viya currently on going.

In general the boosting models need more computing time, but reach the best results looking to the Accuracy of the prediction.
The winner models lastly are:

1. the Stochastic Gradient Boosting with R, reaching an Accuracy of 0.825


2. the Parallel Boosting with Python, reaching an Accuracy of 0.819


3. the Gradient Boosting with Knime, reaching an Accuracy of 0.813

New Company Presentation with Avatar AI

This special presentation of our company is leaded by a modern avatar AI realized with the last ChatGPT, Midjourney & D-ID tools.

Download presentation ppsx version

We hope it could be appreciated.

SAS ready for an IPO in 2025!

SAS ready for an IPO in 2025! After over 50 years! That's a news!

As said directly from Jim Goodnight, CEO at SAS:
"Over the years, SAS has built a reputation for innovation, a relentless focus on the customer, and strong sense of corporate identity. As we chart our path toward IPO-readiness, we will continue to invest in our brand and platform, prioritizing our core values, and empowering customers to solve their most complex problems."
The SAS IPO initially announced for 2024 has been postponed to 2025
Read more in SAS press release.

View recent article

New partnership with KNIME!

Best Open Source software for end to end data science!

Knime has grown in about fifteen years becoming a reference in the world of data scientists who are looking to a consistent solution for their analytical needs. The developing team has done a very good job maintaining the Knime software up do date and open to the most modern cloud platforms, data base, and methodologies. Knime provides hundreds of machine learning algorithms easily configurable in an interface which is simple to navigate and visually attractive!
We are glad to be part of the KNIME partner community starting from may 2021, to share our experience in building analytical models, ETL processes and reports.

View KNIME site

New partnership with MICROSTRATEGY!

One of the best choices among the Analytical and Business Intelligence technologies!

Making data available in smart and appealing interfaces is important as the data analysis itself. That's why, starting from July 2021, Rationence is a Microstrategy partner, which provides business intelligence platforms to create interactive reports and dashboards embedded in web and apps, integrating data analysis with machine learning and data mining features.

View MicroStrategy Site

The Contended Center in our Vision

Rationence continues to hire candidates interested in consulting in all topics related to data analysis.
We are looking for people who are passionate about analytical technologies and Business Intelligence and related topics.
Data mining, machine learning, business process analysis, data integration projects, data warehouse methodology, statistical analysis, architecture and design of web portals, development of dashboards for decision support ... with particular attention to technological integration and innovations, mainly regarding the most recent themes such as Big Data and data processing in the Cloud environment.

Download presentation ppsx version

If you think you are qualified to work with us, please send us your resume at job@rationence.eu. You will find a place of Freedom and Responsibility, Training and Sharing of Knowledge, Proactivity and Participation, Growth and Qualification, Innovation and Creativity, Respect and Professionalism.
The best candidates will be contacted as soon as possible.
Data privacy authorization is required. Past experience and scientific academic qualifications are appreciated.

Partnership SAS.

For Advanced Analytics projects Rationence joined the SAS Global Alliance & Channel Program, becoming in january 2016 reseller partner of SAS, and then moving for the standard Silver Partner Program.

We work mainly for clients belonging to the area of finance, consumer credit, fashion and distribution. The SAS technology is for us the best choice to promote the integration of congruent processes for the exploitation of the wealth of information available to the companies. SAS is essential for the best projects of Analytics, Risk Management, Marketing Automation, Customer Intelligence, and more widely for advanced web reporting, Visual Analytics, Data Management and Data Quality.

View details »

Careers. Opening positions.

We are looking for people passionate for Analytical and Business Intelligence technologies and related themes:
Data Mining, Machine Learning, Business Process analysis, Data Integration projects, Data Warehouse methodology, Statistical Analysis, Web Portal architecture and design, Executive dashboard development ... with a focus on technology integration and innovations, mainly versus Big Data and data processing on clouds environment.

If you think to be qualified to work with us, send us your resume to job@rationence.eu. You will find a place of Freedom and Responsibility, Training and Knowledge Sharing, Pro-Activity and Participation, Growth and Qualification, Innovation and Creativity, Respect and Professionality.

Best candidate will be contacted soon!
Data Privacy authorization is required.

View details »