NPL Management

MONTE TITOLI: ADVANCED ANALYTICS & MACHINE LEARNING ON AWS

Storm Reply and Data Reply supported Monte Titoli to define and develop the adoption strategy of Cloud architectures, governance of resources and ML models.

Download the brochure

Download the brochure

Before filling out the registration form, please read the Privacy notice pursuant to Article 13 of EU Regulation 2016/679

Invalid Input
Invalid Input
Invalid Input
Invalid Input
Invalid Input
Invalid Input
Invalid Input

Privacy


I declare that I have read and fully understood the Privacy Notice and I hereby express my consent to the processing of my personal data by Reply SpA for marketing purposes, in particular to receive promotional and commercial communications or information regarding company events or webinars, using automated contact means (e.g. SMS, MMS, fax, email and web applications) or traditional methods (e.g. phone calls and paper mail).

The challenge

Monte Titoli, the Italian central securities depository (CSD), part of the London Stock Exchange Group and leading provider of post-trade services in Europe, was looking for a fast and secure way to extract value from its data, previously managed on-premises with a classic data warehouse (DWH) approach.

The customer’s final goal was to achieve a flexible and scalable Cloud platform that supported the introduction of advanced predictive and prescriptive analytics pipelines, to scale faster by designing and executing data science projects on Amazon Web Services and to speed up Machine Learning adoption across the organization.

The solution

Monte Titoli chose to rely on Amazon Web Services for its Cloud platform and on Reply, AWS Premier Consulting Partner since 2013,
to define and develop the adoption strategy of Cloud architectures, governance of resources and Machine Learning models.



A Datalake Architecture to Drive Business Decisions Based on Artificial Intelligence

The Datalake architecture, running in production since the beginning of 2019, heavily relies on the AWS serverless approach for orchestration, automation and monitoring purposes giving the infrastructure the agility to scale on-demand based on Business requirements.

The Datalake project was developed and deployed adopting the Agile methodology and DevOps approach and it went live in less than 6 months.

The architecture designed by Storm Reply can be scaled on demand, has zero fixed license costs and a very low management effort since it uses mostly managed and serverless services.

ML platform to design and execute end-to-end ML projects

Data Reply proposed to design a suitable data science workflow adopting Cloud-native services: from data preparation to models implementation, training, serving and monitoring.

Data Reply supported Monte Titoli in implementing a fully-fledged Machine Learning platform on AWS, with Amazon SageMaker as a core component, enabling data scientists to design and execute end-to-end Machine Learning projects both on structured and unstructured data.

This flexible platform enables the development and running of an unlimited number of predictive and prescriptive Machine Learning models. It can serve a large number of internal and external users via both batch and real-time predictions endpoints, scaling with business requirements on-demand.

The results

Leveraging Amazon Web Services and Storm Reply’s expertise, Monte Titoli was able to design and deliver a performant and compliant Datalake Architecture for their business needs to maximise value for their internal and external customers.

The new ML platform developed by Data Reply on AWS lead to a 50% saving of the time required to design and execute a full ML workflow. Moreover, a custom model monitoring controls ML model performance in production, enabling its retraining only when a data drift occurs and reducing models updating costs up to 75%.

  • strip-0

    Monte Titoli

    Monte Titoli, part of the London Stock Exchange Group (LSEG) provides efficient and secure settlement, custody, asset servicing, collateral management and issuer services to domestic and international clients. The company manages a wide range of financial instruments with €3.32 trillion of assets under custody In 2019, processing over 44 million transactions with a year-end settlement rate of 96%.

  • Data Reply

    Data Reply is the Reply Group company that offers excellent services for Big Data and Artificial Intelligence. We operate across most industries and business functions in order to support executive level professionals and Chief Officers to harvest value from data. We build Data Platforms, define and implement ML and AI models in an efficient, replicable and scalable way, by relying upon human resources highly skilled in Big Data Engineering, Data Science and Intelligent Process Automation. Always active on innovations, we are applying Quantum algorithms to support the optimization of processes with high computational needs. www.data.reply.com

    strip-1
  • strip-2

    Storm Reply

    Storm Reply is the company in the Reply Group specialized in the design and implementation of innovative Cloud-based solutions and services. Through consolidated expertise and many years of experience in the creation and management of Infrastructure as a Service (IaaS), Software as a Service (SaaS), and Platform as a Service (PaaS) Cloud solutions, Storm Reply supports important companies in Europe and all over the world in the implementation of Cloud-based systems and applications. www.storm.reply.com

Monte Titoli: Advanced Analytics and Machine Learning on AWS

Download the brochure