Innovation and technology nurture each other.

We harness the power of data for better decision making within an innovative organizational culture, through our team of Data Architects, Data Scientists and Data Engineers.

This evolves into gigantic volumes of data, which using the tools provided by the cloud allows us not only to improve its analysis but also to implement Machine Learning and AI to increase business intelligence.

Intelligent Forecasting

AI solution that allows the forecasting of business events in advance in order to plan improvements and actions that optimize results.

Data Lakes

Business analysis, manage diverse data sources, and achieve a better understanding of the world through these centralized repositories.

Master Data Optimization

The Master Data Optimization solution uses Machine Learning to automate the creation, remediation and continuous maintenance of master databases.

HealthBot

Virtual health channel that uses cognitive technologies such as artificial intelligence, in order to optimize and speed up the times of health institutions.

Generative AI

Discover the technological disruption that allows you to take your business to a new level and achieve maximum productivity.

Intelligent Automation

Robotic Process Automation (RPA) and Artificial Intelligence that empower a rapid automation of end-to-end business processes and accelerate digital transformation.

Nubiral Cognitive AI Bot

Virtual conversational assistant based on Artificial Intelligence (AI) that enables real-time file processing.

Intelligent Document Processing

An AI solution that allows extracting information from documents and incorporating it into an automatic process, using OCR technology.

Intelligent Forecasting for demand planning

An insurance company performs demand forecasting in its various business units and reduces forecasting errors.

Read more

Anomaly detection through Data Lake and Fraud Detector

An important insurance company in Mexico detects anomalies and prevents actions with a probability of being fraudulent.

Read more

Application of multivariate models to improve delinquency and loss

Improvement of delinquency and loss indicators through the application of multivariate models that analyze different aspects of clients.

Read more

Detection and correction of fraud using Fraud Detector

Fraud prevention using a machine learning model created by Nubiral: Fraud Detector.

Read more
Blog

Generative AI: Code Development Scope

How this technology impacts the creation of code in different industries, particularly in financial services.

Read more
eBooks

MLOps: powering the value of machine learning

A comprehensive guide to MLOps, a key discipline that guarantees the success of Machine Learning (ML) projects in organizations.

Read more
Papers

Trends 2024: Start getting value from generative AI

Over the next 12 months, we will witness an incremental adoption of generative AI, higher levels of maturity and new use cases.

Read more
Whitepapers

Microsoft Fabric Guide: Use case end-to-end Deployment

Banks and financial services companies can benefit in numerous ways by deploying Microsoft Fabric.

Read more

Learn about our architecture that combines at least one public and one private cloud to deliver the highest levels of scalability, flexibility, and performance.

Application modernization by migrating to the AWS cloud

Migration to the AWS Cloud at Telecom Argentina, modernizing obsolete applications with a focus on operational excellence.

Read more

Modernization of multimedia content with AWS Migration

Successful migration to AWS cloud to modernize Claro Video’s multimedia content infrastructure.

Read more

Migration to AWS by a major Japanese automobile company

The smooth migration of Toyota to AWS unleashes performance, cost efficiency, and user satisfaction.

Read more

An important logistics company migrates its systems to AWS

OCA Argentina relies on legacy systems with limited cloud integration, so it modernized its technology by migrating to AWS.

Read more
Blog

5 benefits of serverless architectures

Higher levels of scalability and an absolute focus on digital business transformation, are just some of the many advantages of this model.

Read more
eBooks

Cloud 4.0: A phenomenon in exponential growth

A tour of the main opportunities that arise from a correct and timely migration of workloads to the cloud, and the trends that are being visualized in the cloud universe.

Read more
Papers
04 October , 2022

Cloud 4.0: A phenomenon in exponential growth

A tour of the main opportunities that arise from a correct and timely migration of workloads to the cloud, and the trends that are being visualized in the cloud universe.

Read more

Application migration, optimization, efficiency, security, analytics and implementation services, with the aim of simplifying and accelerating the adoption of the latest IT trends in the market.

Planning and Consulting

  • Evaluation and Planning
  • Adoption Strategy Consultancy

Test

  • Test Automation

Execution

  • Design and implementation of CI/CD Pipeline
  • Automation and implementation of processes

App Dev

  • Code (JavaScript, Go, Python)

Telecommunications modernization with AWS technologies

A leading telecommunications company modernizes its applications to respond more quickly and agilely to market changes.

Read more

App Modernization in Telecommunications and Entertainment

A prominent telecommunications and entertainment company achieved billing app availability levels of 99.95% in Colombia.

Read more

Azure Governance & App Modernization

A leading telecommunications and entertainment company achieved application billing availability levels of 99.95%.

Read more

Migration deployment of Core Banking hosted in the AWS cloud

Fintech deploys the Core Banking of its platform allowing the integration of new services in an effective and easy way.

Read more
Blog

The importance of containers in modernization

A way to lower costs, generate efficiency and accelerate transformation when migrating legacy systems or upgrading applications.

Read more
eBooks

Agile & DevOps

A review of the meanings of each of these concepts, how they integrate with each other and what benefits they bring.

Read more

As ZABBIX Certified Partners, we scale to environments with thousands of items monitored simultaneously.
We also capture data of systems and applications over time to make proactive decisions and to anticipate disruptions in business services.

  • Zabbix Architecture and Implementation
  • Data & Analytics Monitoring

Monitoring solution upgrade using Zabbix

Migration of monitoring tool to an automated system for host discovery, dashboards, and scalability over time.

Read more

Telephone exchange monitoring, usage metrics, and channels

Monitoring of AVAYA phone system through the implementation of Zabbix, executing the only method of information extraction via telnet manager.

Read more

Implementation of monitoring solution with Zabbix

A leading payment solutions company implements a new automated monitoring platform equipped with a real-time messaging alert system for incident prevention.

Read more

IT Resource Monitoring Platform

Monitoring & Intelligence | Insurance | Zabbix IT Resource Monitoring Platform Integration of Zabbix with the VMWare solution and monitoring of PABX trunk lines from providers, UPS equipment, and Chillers....
Read more
Blog

System Monitoring: the 5 most anticipated features for Zabbix 6.4

System monitoring is a critical task for any company that wants to make sure its systems are working properly. What’s new in the 6.4 version of Zabbix?

Read more
eBooks

Compliance: the evolution of monitoring

A key paradigm for anticipating and solving problems in increasingly complex IT infrastructures.

Read more
Whitepapers

OpenSearch and its log agents

OpenSearch is a comprehensive solution for centralizing and analyzing logs from various sources, ideal for managing complex IT scenarios.

Read more

We help innovate by preparing our clients against current cyber threats.

We fulfill the responsibility of protecting data to maintain trust and comply with regulations.

  • Cloud Assessment & Consulting
  • Security Frameworks & Best Practices
  • Penetration Testing
  • Cloud Security
  • DevSecOps
Blog

Cybersecurity: Key Pillar for a 360º Digital Experience

To mitigate the risks associated with cyberattacks and protect data is essential to survive and lead in the era of digital transformation.

Read more
Whitepapers

Cybersecurity in your company: The 360º digital solution from Nubiral

How to develop a cybersecurity plan? Which are the main threats? Which are the best and most modern technologies to face these threats?

Read more

Generative AI: Code Development Scope

How this technology impacts the creation of code in different industries, particularly in financial services.

Read more

Bringing light to dark data: how to use it for business growth

Companies often collect data that they generally do not use for any purpose. It’s called “dark data” and it can be key to improving business.

Read more

Microsoft Fabric: Empowering business users

In the era of AI-driven business, this unified data analytics platform empowers every team to get the most value from data.

Read more

Generative AI: Code Development Scope

How this technology impacts the creation of code in different industries, particularly in financial services.

Read more

MLOps: powering the value of machine learning

A comprehensive guide to MLOps, a key discipline that guarantees the success of Machine Learning (ML) projects in organizations.

Read more

DataOps: everyone plays their own game

Discover how this discipline provides a framework and tools to align the engineering and analytics teams to improve the management of the data ecosystem in the organization.

Read more

GenAI Services: A land of opportunity for organizations.

The new user-friendly way to adopt generative artificial intelligence to power business.

Read more

Intelligent Document Processing

Converting contained data into business-valuable documents. The power of combining document management and artificial intelligence.

Read more

Connect+ is a great tool to incorporate knowledge and stay up to date with the latest technological developments.

Access new innovative audiovisual content, quickly and easily. Explore and get to know the technological universe in a different and agile way!

Cybersecurity in your company: The 360º digital solution from Nubiral

How to develop a cybersecurity plan? Which are the main threats? Which are the best and most modern technologies to face these threats?

Read more

Microsoft Fabric Guide: Use case end-to-end Deployment

Banks and financial services companies can benefit in numerous ways by deploying Microsoft Fabric.

Read more

How to Deploy Microsoft Fabric in Multicloud Infrastructures

Microsoft Fabric’s data analytics combined with the power of the multi-cloud architecture, drives decision making and empowers users.

Read more

OpenSearch and its log agents

OpenSearch is a comprehensive solution for centralizing and analyzing logs from various sources, ideal for managing complex IT scenarios.

Read more

AWS + Nubiral

As an Advanced Consulting Partner of the AWS Partner Network, we think outside the box, daring to go where no one has gone before.
We constantly challenge ourselves to be better, providing your company with AWS solutions in a holistic and tailored way.

Microsoft + Nubiral

As Cloud Gold Partner, we work together with Microsoft every day to offer our clients the most innovative solutions based on the different microservices and capabilities that the Azure cloud offers.
Our team is constantly training and certifying on Azure’s services.

Zabbix + Nubiral

As ZABBIX Certified Partners, we scale to environments with thousands of items monitored simultaneously.
We also capture data of systems and applications over time to make proactive decisions and to anticipate disruptions in business services.

Data
& Innovation

General Info

Innovation and technology nurture each other.

We harness the power of data for better decision making within an innovative organizational culture, through our team of Data Architects, Data Scientists and Data Engineers.

This evolves into gigantic volumes of data, which using the tools provided by the cloud allows us not only to improve its analysis but also to implement Machine Learning and AI to increase business intelligence.

Solutions

Intelligent Forecasting

AI solution that allows the forecasting of business events in advance in order to plan improvements and actions that optimize results.

Data Lakes

Business analysis, manage diverse data sources, and achieve a better understanding of the world through these centralized repositories.

Master Data Optimization

The Master Data Optimization solution uses Machine Learning to automate the creation, remediation and continuous maintenance of master databases.

HealthBot

Virtual health channel that uses cognitive technologies such as artificial intelligence, in order to optimize and speed up the times of health institutions.

Generative AI

Discover the technological disruption that allows you to take your business to a new level and achieve maximum productivity.

Intelligent Automation

Robotic Process Automation (RPA) and Artificial Intelligence that empower a rapid automation of end-to-end business processes and accelerate digital transformation.

Nubiral Cognitive AI Bot

Virtual conversational assistant based on Artificial Intelligence (AI) that enables real-time file processing.

Intelligent Document Processing

An AI solution that allows extracting information from documents and incorporating it into an automatic process, using OCR technology.

Success Stories

Intelligent Forecasting for demand planning

An insurance company performs demand forecasting in its various business units and reduces forecasting errors.

Read more

Anomaly detection through Data Lake and Fraud Detector

An important insurance company in Mexico detects anomalies and prevents actions with a probability of being fraudulent.

Read more

Application of multivariate models to improve delinquency and loss

Improvement of delinquency and loss indicators through the application of multivariate models that analyze different aspects of clients.

Read more

Detection and correction of fraud using Fraud Detector

Fraud prevention using a machine learning model created by Nubiral: Fraud Detector.

Read more

Connect

Blog

Generative AI: Code Development Scope

How this technology impacts the creation of code in different industries, particularly in financial services.

Read more
eBooks

MLOps: powering the value of machine learning

A comprehensive guide to MLOps, a key discipline that guarantees the success of Machine Learning (ML) projects in organizations.

Read more
Papers

Trends 2024: Start getting value from generative AI

Over the next 12 months, we will witness an incremental adoption of generative AI, higher levels of maturity and new use cases.

Read more
Whitepapers

Microsoft Fabric Guide: Use case end-to-end Deployment

Banks and financial services companies can benefit in numerous ways by deploying Microsoft Fabric.

Read more

Hybrid
Multi Cloud

General Info

Learn about our architecture that combines at least one public and one private cloud to deliver the highest levels of scalability, flexibility, and performance.

Success Stories

Application modernization by migrating to the AWS cloud

Migration to the AWS Cloud at Telecom Argentina, modernizing obsolete applications with a focus on operational excellence.

Read more

Modernization of multimedia content with AWS Migration

Successful migration to AWS cloud to modernize Claro Video’s multimedia content infrastructure.

Read more

Migration to AWS by a major Japanese automobile company

The smooth migration of Toyota to AWS unleashes performance, cost efficiency, and user satisfaction.

Read more

An important logistics company migrates its systems to AWS

OCA Argentina relies on legacy systems with limited cloud integration, so it modernized its technology by migrating to AWS.

Read more

Connect

Blog

5 benefits of serverless architectures

Higher levels of scalability and an absolute focus on digital business transformation, are just some of the many advantages of this model.

Read more
eBooks

Cloud 4.0: A phenomenon in exponential growth

A tour of the main opportunities that arise from a correct and timely migration of workloads to the cloud, and the trends that are being visualized in the cloud universe.

Read more
Papers
04 October , 2022

Cloud 4.0: A phenomenon in exponential growth

A tour of the main opportunities that arise from a correct and timely migration of workloads to the cloud, and the trends that are being visualized in the cloud universe.

Read more

DevOps
& App Evolution

General Info

Application migration, optimization, efficiency, security, analytics and implementation services, with the aim of simplifying and accelerating the adoption of the latest IT trends in the market.

Solutions

Planning and Consulting

  • Evaluation and Planning
  • Adoption Strategy Consultancy

Test

  • Test Automation

Execution

  • Design and implementation of CI/CD Pipeline
  • Automation and implementation of processes

App Dev

  • Code (JavaScript, Go, Python)

Success Stories

Telecommunications modernization with AWS technologies

A leading telecommunications company modernizes its applications to respond more quickly and agilely to market changes.

Read more

App Modernization in Telecommunications and Entertainment

A prominent telecommunications and entertainment company achieved billing app availability levels of 99.95% in Colombia.

Read more

Azure Governance & App Modernization

A leading telecommunications and entertainment company achieved application billing availability levels of 99.95%.

Read more

Migration deployment of Core Banking hosted in the AWS cloud

Fintech deploys the Core Banking of its platform allowing the integration of new services in an effective and easy way.

Read more

Connect

Blog

The importance of containers in modernization

A way to lower costs, generate efficiency and accelerate transformation when migrating legacy systems or upgrading applications.

Read more
eBooks

Agile & DevOps

A review of the meanings of each of these concepts, how they integrate with each other and what benefits they bring.

Read more

Monitoring
& Intelligence

General Info

As ZABBIX Certified Partners, we scale to environments with thousands of items monitored simultaneously.
We also capture data of systems and applications over time to make proactive decisions and to anticipate disruptions in business services.

Solutions

  • Zabbix Architecture and Implementation
  • Data & Analytics Monitoring

Success Stories

Monitoring solution upgrade using Zabbix

Migration of monitoring tool to an automated system for host discovery, dashboards, and scalability over time.

Read more

Telephone exchange monitoring, usage metrics, and channels

Monitoring of AVAYA phone system through the implementation of Zabbix, executing the only method of information extraction via telnet manager.

Read more

Implementation of monitoring solution with Zabbix

A leading payment solutions company implements a new automated monitoring platform equipped with a real-time messaging alert system for incident prevention.

Read more

IT Resource Monitoring Platform

Monitoring & Intelligence | Insurance | Zabbix IT Resource Monitoring Platform Integration of Zabbix with the VMWare solution and monitoring of PABX trunk lines from providers, UPS equipment, and Chillers....
Read more

Connect

Blog

System Monitoring: the 5 most anticipated features for Zabbix 6.4

System monitoring is a critical task for any company that wants to make sure its systems are working properly. What’s new in the 6.4 version of Zabbix?

Read more
eBooks

Compliance: the evolution of monitoring

A key paradigm for anticipating and solving problems in increasingly complex IT infrastructures.

Read more
Whitepapers

OpenSearch and its log agents

OpenSearch is a comprehensive solution for centralizing and analyzing logs from various sources, ideal for managing complex IT scenarios.

Read more

Cybersecurity

General Info

We help innovate by preparing our clients against current cyber threats.

We fulfill the responsibility of protecting data to maintain trust and comply with regulations.

Solutions

  • Cloud Assessment & Consulting
  • Security Frameworks & Best Practices
  • Penetration Testing
  • Cloud Security
  • DevSecOps

Connect

Blog

Cybersecurity: Key Pillar for a 360º Digital Experience

To mitigate the risks associated with cyberattacks and protect data is essential to survive and lead in the era of digital transformation.

Read more
Whitepapers

Cybersecurity in your company: The 360º digital solution from Nubiral

How to develop a cybersecurity plan? Which are the main threats? Which are the best and most modern technologies to face these threats?

Read more

Partners

Solutions

AWS + Nubiral

As an Advanced Consulting Partner of the AWS Partner Network, we think outside the box, daring to go where no one has gone before.
We constantly challenge ourselves to be better, providing your company with AWS solutions in a holistic and tailored way.

Microsoft + Nubiral

As Cloud Gold Partner, we work together with Microsoft every day to offer our clients the most innovative solutions based on the different microservices and capabilities that the Azure cloud offers.
Our team is constantly training and certifying on Azure’s services.

Zabbix + Nubiral

As ZABBIX Certified Partners, we scale to environments with thousands of items monitored simultaneously.
We also capture data of systems and applications over time to make proactive decisions and to anticipate disruptions in business services.

Success Stories

Intelligent Forecasting for process automation

Solution enabling the automation of demand planning processes across various business units within the company.

Read more

A medical center implements a chatbot and cognitive services

Improvement in patient care times and reduction in administrative staff dedication costs for routine tasks.

Read more

Monitoring solution upgrade using Zabbix

Migration of monitoring tool to an automated system for host discovery, dashboards, and scalability over time.

Read more

Connect

Blog

Generative AI: Code Development Scope

How this technology impacts the creation of code in different industries, particularly in financial services.

Read more

Bringing light to dark data: how to use it for business growth

Companies often collect data that they generally do not use for any purpose. It’s called “dark data” and it can be key to improving business.

Read more

Microsoft Fabric: Empowering business users

In the era of AI-driven business, this unified data analytics platform empowers every team to get the most value from data.

Read more

Generative AI: Code Development Scope

How this technology impacts the creation of code in different industries, particularly in financial services.

Read more

eBooks & Papers

MLOps: powering the value of machine learning

A comprehensive guide to MLOps, a key discipline that guarantees the success of Machine Learning (ML) projects in organizations.

Read more

DataOps: everyone plays their own game

Discover how this discipline provides a framework and tools to align the engineering and analytics teams to improve the management of the data ecosystem in the organization.

Read more

GenAI Services: A land of opportunity for organizations.

The new user-friendly way to adopt generative artificial intelligence to power business.

Read more

Intelligent Document Processing

Converting contained data into business-valuable documents. The power of combining document management and artificial intelligence.

Read more

Connect+

Connect+ is a great tool to incorporate knowledge and stay up to date with the latest technological developments.

Access new innovative audiovisual content, quickly and easily. Explore and get to know the technological universe in a different and agile way!

Whitepapers

Cybersecurity in your company: The 360º digital solution from Nubiral

How to develop a cybersecurity plan? Which are the main threats? Which are the best and most modern technologies to face these threats?

Read more

Microsoft Fabric Guide: Use case end-to-end Deployment

Banks and financial services companies can benefit in numerous ways by deploying Microsoft Fabric.

Read more

How to Deploy Microsoft Fabric in Multicloud Infrastructures

Microsoft Fabric’s data analytics combined with the power of the multi-cloud architecture, drives decision making and empowers users.

Read more

OpenSearch and its log agents

OpenSearch is a comprehensive solution for centralizing and analyzing logs from various sources, ideal for managing complex IT scenarios.

Read more
Whitepapers

Machine learning recommender systems in digital media companies

Advances in machine learning enable digital media companies to improve their recommender systems and optimize user experience.

Home / Machine learning recommender systems in digital media companies

1. Introduction: Towards a more personalized experience

Much of the success of digital media companies is based on their recommender systems. In recent times they have become an essential tool for personalizing the user experience on platforms, e-commerce and social networks.

These systems analyze behavior patterns and preferences to suggest products, movies, articles and more. As users, we already recognize the messages from streaming platforms. “If you liked this, we recommend…”.

However, we are just at the beginning of the journey. The increasing complexity of user preferences and expanding content catalogs, demand more sophisticated approaches.

This is where advanced machine learning (ML) technologies and large language models (LLMs) come into play. This guide explores how it is possible to use these technologies to develop recommender systems with the highest levels of accuracy and personalization.

2. Basics of recommender systems

In general, we identify two types of recommender systems.

1- Collaborative filtering. This is the classical approach. It is based on the premise that if two users have had similar interests in the past, they are likely to repeat such matches in the future. These methods use the matrix of user-element interactions to record and learn from past interactions. However, on their own, they can be limited, particularly when encountering new users or elements (this is known as the “cold start problem”).

2- Content-based filtering. Unlike the previous one, it uses additional information about users and items. For example, in a movie recommendation system, this could include directors or actors, among other variables. These methods can provide more personalized recommendations. This is because they consider the specific characteristics of features that have appealed to individual users in the past.

3. New technologies: LLM and embeddings

In a world where technologies are evolving rapidly, innovations are emerging that are set to change the rules of the game. Recommender systems are reaching new levels.

– LLM: natural language understanding. These models, including GPT, Bert and Titan, are revolutionary. In particular because of their ability to understand and generate natural language.

Based on the transformer architecture, they can process sequences of words, capturing complex contexts and relationships. In recommender systems, they play an essential role in better understanding descriptions, reviews and metadata. Thus, they provide a deeper understanding of both content and user preferences.

– Embeddings: capturing semantic meaning. Embeddings are vector representations of text that capture semantic meanings and contextual associations. In a recommender system, converting item descriptions and user preferences into embeddings allows similarities and differences to be calculated efficiently. This not only improves the accuracy of recommendations but also helps to overcome the “cold start problem”. This is because it allows comparisons with new items or users. Let’s look at how this applies specifically to the digital media industry. These companies have valuable information about their content in both synopsis and metadata. For example, the actors that participate in each episode of each series or in each movie. Embeddings allow to capture all this information to produce a more assertive system.

 

4. Hands-on implementation

What are the next steps?

– Integration of LLM into recommender systems. To do so, it is first necessary to fit a pre-trained model with the organization’s own data. In addition to being pre-trained with a vast amount of content, many of these models allow us to perform fine tuning. This involves adapting that training to fit the organizational data. Therefore, it is possible to train these models with the historical data of the users so that they can learn about their tastes and, based on that, predict what will be the next content to be chosen by each of them. This is how the recommendation system is built.

– Construction and use of embeddings. To build a content-based approach, we have the help of embeddings. These are the ones that allow us to transform the texts related to the content (descriptions, reviews, among others) into numerical vectors. To do so, they use a specific model, such as Ada or Titan. Then, we are able to map all our available items in the same space, but always maintaining the semantic difference between them. Subsequently, it is possible to use these embeddings to feed machine learning algorithms that predict user preferences. For example, calculating the cosine similarity between the vector representing the user to each vector representing each different content, so as to recommend those closest in the semantic space and as a result those that have a higher similarity with the user’s profile.

5. How can a recommender help in an app?

Digital media companies that incorporate a recommender in their app gain access to the following benefits:

– Prioritize the user experience. Indeed, the user is at the center of the strategy, since the suggested content is accurate according to their tastes, needs and behaviors. This increases loyalty and satisfaction levels.

– Better strategic consumption of content. Combined with the specific needs of the business, the recommender can drive the consumption of certain strategic content with a high level of precision.

– More performing systems. At Nubiral we are working on developing a recommendation system that focuses on these new technologies. What we have been able to prove is that in this way, more performing systems are obtained. We take advantage of the ability of this new technology to capture the semantic meaning and include information about the content. This often comes in natural language, such as user reviews. This allowed us to build a recommender that considers all available information, both from users and from the available content to be recommended. After testing in scenarios with real users, we were able to improve by up to 20% the rate of clicks made by users on the recommendations. In other words, we obtained a 20% more assertive recommendation system.

6. Conclusions: looking into the future

Recommendation systems are an integral part of the user experience, and their importance will continue to grow as digital platforms do.

New technologies, as we have already seen, offer significant promises for improving the accuracy and personalization of these recommendations.

However, it is vital to address this concept with a balanced approach, recognizing both its potential and its limitations.

The field of ML and recommender systems is constantly evolving. Companies in the digital media industry need to keep up to date in this regard if they want to continue to succeed in their business.

Our experts can help you get the most value from these technological advances. We look forward to hearing from you: Schedule your meeting!

Machine learning recommender systems in digital media companies


 

  1. Introduction: towards a more personalized experience

Much of the success of digital media companies is based on their recommender systems. In recent times they have become an essential tool for personalizing the user experience on platforms, e-commerce and social networks.

These systems analyze behavior patterns and preferences to suggest products, movies, articles and more. As users, we already recognize the messages from streaming platforms. “If you liked this, we recommend…”.

However, we are just at the beginning of the journey. The increasing complexity of user preferences and expanding content catalogs, demand more sophisticated approaches.

This is where advanced machine learning (ML) technologies and large language models (LLMs) come into play. This guide explores how it is possible to use these technologies to develop recommender systems with the highest levels of accuracy and personalization.

 

  1. Basics of recommender systems

In general, we identify two types of recommender systems.

 Collaborative filtering. This is the classical approach. It is based on the premise that if two users have had similar interests in the past, they are likely to repeat such matches in the future. These methods use the matrix of user-element interactions to record and learn from past interactions. However, on their own, they can be limited, particularly when encountering new users or elements (this is known as the “cold start problem”).

Content-based filtering. Unlike the previous one, it uses additional information about users and items. For example, in a movie recommendation system, this could include directors or actors, among other variables. These methods can provide more personalized recommendations. This is because they consider the specific characteristics of features that have appealed to individual users in the past.

  

  1. New technologies: LLM and embeddings

 In a world where technologies are evolving rapidly, innovations are emerging that are set to change the rules of the game. Recommender systems are reaching new levels.

 – LLM: natural language understanding. These models, including GPT, Bert and Titan, are revolutionary. In particular because of their ability to understand and generate natural language.

 Based on the transformer architecture, they can process sequences of words, capturing complex contexts and relationships. In recommender systems, they play an essential role in better understanding descriptions, reviews and metadata. Thus, they provide a deeper understanding of both content and user preferences.

 – Embeddings: capturing semantic meaning. Embeddings are vector representations of text that capture semantic meanings and contextual associations. In a recommender system, converting item descriptions and user preferences into embeddings allows similarities and differences to be calculated efficiently. This not only improves the accuracy of recommendations but also helps to overcome the “cold start problem”. This is because it allows comparisons with new items or users. Let’s look at how this applies specifically to the digital media industry. These companies have valuable information about their content in both synopsis and metadata. For example, the actors that participate in each episode of each series or in each movie. Embeddings allow to capture all this information to produce a more assertive system.

 

  1. Hands-on implementation

What are the next steps?

– Integration of LLM into recommender systems. To do so, it is first necessary to fit a pre-trained model with the organization’s own data. In addition to being pre-trained with a vast amount of content, many of these models allow us to perform fine tuning. This involves adapting that training to fit the organizational data. Therefore, it is possible to train these models with the historical data of the users so that they can learn about their tastes and, based on that, predict what will be the next content to be chosen by each of them. This is how the recommendation system is built.

– Construction and use of embeddings. To build a content-based approach, we have the help of embeddings. These are the ones that allow us to transform the texts related to the content (descriptions, reviews, among others) into numerical vectors. To do so, they use a specific model, such as Ada or Titan. Then, we are able to map all our available items in the same space, but always maintaining the semantic difference between them. Subsequently, it is possible to use these embeddings to feed machine learning algorithms that predict user preferences. For example, calculating the cosine similarity between the vector representing the user to each vector representing each different content, so as to recommend those closest in the semantic space and as a result those that have a higher similarity with the user’s profile.

 

  1. How can a recommender help in an app?

Digital media companies that incorporate a recommender in their app gain access to the following benefits:

– Prioritize the user experience. Indeed, the user is at the center of the strategy, since the suggested content is accurate according to their tastes, needs and behaviors. This increases loyalty and satisfaction levels.

– Better strategic consumption of content. Combined with the specific needs of the business, the recommender can drive the consumption of certain strategic content with a high level of precision.

– More performing systems. At Nubiral we are working on developing a recommendation system that focuses on these new technologies. What we have been able to prove is that in this way, more performing systems are obtained. We take advantage of the ability of this new technology to capture the semantic meaning and include information about the content. This often comes in natural language, such as user reviews. This allowed us to build a recommender that considers all available information, both from users and from the available content to be recommended. After testing in scenarios with real users, we were able to improve by up to 20% the rate of clicks made by users on the recommendations. In other words, we obtained a 20% more assertive recommendation system.

 

  1. Conclusions: looking into the future

Recommendation systems are an integral part of the user experience, and their importance will continue to grow as digital platforms do.

New technologies, as we have already seen, offer significant promises for improving the accuracy and personalization of these recommendations.

However, it is vital to address this concept with a balanced approach, recognizing both its potential and its limitations.

The field of ML and recommender systems is constantly evolving. Companies in the digital media industry need to keep up to date in this regard if they want to continue to succeed in their business.

Our experts can help you get the most value from these technological advances. We look forward to hearing from you: Schedule your meeting!

Complete the form and we will contact you shortly.

Nubiral

About Nubiral