Pro-Lar
Pro-Lar is a suite of integratable AI/ML services aimed at generating actionable customer insights and increasing operational efficiency. These include, but are not limited to, recommender systems, churn prediction models, customer segmentation models and data disambiguation services, as well as modules which recommend intervention strategies for our churn prediction service.
Features
- Fully-integratable recommendation engine
- Customer insights analytics tool and dashboard
- ML engine to identify customers at risk of churn
- AI tool that suggests intervention approaches
- Customer segmentation model
- Automated model retraining pipeline
- RESTful API tailored according to client's requirements
- Product/service ideation workshops and consulting service
- Customer onboarding tool powered by AI
Benefits
- Increase customer spend and loyalty through bespoke machine leaning reccomendations
- Benefit from AI and Machine Learning without needing in-house expertise
- Improve customer retention rates through our churn prediction service
- Improve your customer's expereince through machine-learning powered customer personalisaton
- Integrate bespoke Machine Learning models into your business through APIs
- Use behavioural segmentation to understand customers better
Pricing
£5,000 a unit a month
- Education pricing available
Service documents
Request an accessible format
Framework
G-Cloud 13
Service ID
6 3 4 3 6 3 8 5 7 1 7 2 3 9 2
Contact
Pivigo
Neil Forrest
Telephone: 07889563156
Email: neil.forrest@pivigo.com
Service scope
- Software add-on or extension
- No
- Cloud deployment model
- Public cloud
- Service constraints
- N/A
- System requirements
-
- General modern computer operating system (Windows, OSX, Linux, etc)
- Internet connection and general modern web browser (IE, Chrome, etc)
- SFTP client and ability to generate OpenSSH public SSH key
User support
- Email or online ticketing support
- Email or online ticketing
- Support response times
- Pivigo provides its standard Incident Management support service Monday to Friday (excluding UK Public Holidays) between 08.00 and 18.00. Response times are between 1 hour and 8 hours depending upon urgency and impact.
- User can manage status and priority of support tickets
- Yes
- Online ticketing support accessibility
- None or don’t know
- Phone support
- No
- Web chat support
- No
- Onsite support
- No
- Support levels
-
For each of our clients we provide access to a named Customer Success Manager who works with the client to perform account management duties both at a project/technical level as well as a customer service and commercial level.
We provide standard Incident Management support service Monday to Friday (excluding UK Public Holidays) between 08.00 and 18.00.
Our response and resolution times are as follows:
P1 1 hour response and 24 hour mean-time-to-recovery
P2 2 hour response and 48 hour mean-time-to-recovery
P3 3 hour response and 3 day mean-time-to-recovery
Priority is determined by an Urgency over Impact matrix whereby:
P1 Urgency High and Impact High
P2 Urgency Low and Impact High
P2 Urgency High and Impact Low
P3 Urgency Low and Impact Low - Support available to third parties
- No
Onboarding and offboarding
- Getting started
- In all projects delivered by Pivigo, the Buyer plays a critical role throughout the solution design and delivery processes. In short, our goal is to ensure that our solutions meet the unique requirements of the user, so understanding how the user will consume the product is a critical part of the process. Before we build your solution our on-boarding team will sit down with the Buyer to understand the business case: the challenges we aim to address and the strategic goals driving the requirement. Our data scientists will put the supporting data through a stringent health-check to ensure that it is fit-for-purpose for the modelling tasks ahead.
- Service documentation
- Yes
- Documentation formats
-
- HTML
- ODF
- End-of-contract data extraction
- Any data not auto-pruned will be returned or destroyed in a manner agreed with the user and evidence of said actions documented.
- End-of-contract process
-
The user shall immediately cease to access the Pivigo Cloud (if applicable) and cease all use of the AI Solution, and Pivigo shall be entitled to delete the instance or tenant or configuration of the AI Solution and Partner Content and any Outputs where the same are hosted on a Partner Cloud Environment.
Evidence of Pivigo's close-down process including data deletion, provided to the user upon request.
Using the service
- Web browser interface
- Yes
- Supported browsers
-
- Internet Explorer 11
- Microsoft Edge
- Firefox
- Chrome
- Safari
- Opera
- Application to install
- No
- Designed for use on mobile devices
- No
- Service interface
- No
- User support accessibility
- None or don’t know
- API
- No
- Customisation available
- Yes
- Description of customisation
- Users can customise the look and feel, as well as some data fields and outputs
Scaling
- Independence of resources
- Pivigo ensures that users are not affected by other users of our platform by provisioning dedicated compute resource for each environment used by our clients. As such each of our client’s services are logically distinct from each other and within the client service the ‘staging’ and ‘production’ environments are similarly distinct. We also deploy all services into multi-availability zone Cloud regions and configure load balancing to distribute load according to demand.
Analytics
- Service usage metrics
- Yes
- Metrics types
- Availability, n tickets, accuracy
- Reporting types
- Regular reports
Resellers
- Supplier type
- Not a reseller
Staff security
- Staff security clearance
- Other security clearance
- Government security clearance
- Up to Security Clearance (SC)
Asset protection
- Knowledge of data storage and processing locations
- Yes
- Data storage and processing locations
- United Kingdom
- User control over data storage and processing locations
- Yes
- Datacentre security standards
- Supplier-defined controls
- Penetration testing frequency
- At least once a year
- Penetration testing approach
- In-house
- Protecting data at rest
- Encryption of all physical media
- Data sanitisation process
- Yes
- Data sanitisation type
- Deleted data can’t be directly accessed
- Equipment disposal approach
- A third-party destruction service
Data importing and exporting
- Data export approach
- The user can export their data through their SFTP port.
- Data export formats
-
- CSV
- Other
- Other data export formats
- JSON
- Data import formats
-
- CSV
- Other
- Other data import formats
- JSON
Data-in-transit protection
- Data protection between buyer and supplier networks
- TLS (version 1.2 or above)
- Data protection within supplier network
- TLS (version 1.2 or above)
Availability and resilience
- Guaranteed availability
- Subject to, and expressly excluding downtime due to maintenance, if the Actual Uptime Percentage for an AI Solution (made available through Pivigo Cloud) in any Service Month is lower than 99.5%, Pivigo will credit the Partner an amount equal to the monthly Charges paid by the Partner for that AI Solution in the Service Month multiplied by a percentage equal to the difference between the Availability Service Level and the Actual Uptime Percentage for that Service Month and capped at 15%. e.g. If the Actual Uptime Percentage is 98.5, the Service Credit will be 1% of the monthly Charges paid for the subscription to the relevant AI Solution.
- Approach to resilience
- All of our customer deployments take advantage of multi-availability zone locations and also load balancing in the Cloud. Should the service fail in one of the availability zones traffic is routed to the remaining deployment and as necessary the service is auto-scaled to ensure service demand can be maintained. In addition the deployments themselves take advantage of 'infrastructure-as-code' which also allows us to redeploy into additional Cloud regions should there be a more persistent issues within the current Cloud region.
- Outage reporting
- Email alerts
Identity and authentication
- User authentication needed
- Yes
- User authentication
- Username or password
- Access restrictions in management interfaces and support channels
-
Access to the system is typically restricted to the customer's public IP address and where interactive login is required secured with a username and password.
The accounts used to connect via SCP/SFTP are provisioned as part of the service initiation process - including the inclusion of the SSH public key as well as IP whitelists. - Access restriction testing frequency
- At least once a year
- Management access authentication
- Username or password
Audit information for users
- Access to user activity audit information
- Users contact the support team to get audit information
- How long user audit data is stored for
- Between 1 month and 6 months
- Access to supplier activity audit information
- Users contact the support team to get audit information
- How long supplier audit data is stored for
- Between 1 month and 6 months
- How long system logs are stored for
- Between 1 month and 6 months
Standards and certifications
- ISO/IEC 27001 certification
- No
- ISO 28000:2007 certification
- No
- CSA STAR certification
- No
- PCI certification
- No
- Cyber essentials
- No
- Cyber essentials plus
- No
- Other security certifications
- No
Security governance
- Named board-level person responsible for service security
- Yes
- Security governance certified
- No
- Security governance approach
- We follow industry best-practice including least access / privilege, white-listing and encryption
- Information security policies and processes
- Escalation of an incident would be conducted via the Customer Success Manager allocated to the customer's account. In the event of a security incident (deemed a P1) our senior management team is also raised to coordinate the investigation, remedial actions and also conduct a post-mortem (including a Root Cause Analysis) - the primary aim being to identify what process changes are required to avoid future occurrences as well as ensure our response is robust and ensures the client’s interests are maintained.
Operational security
- Configuration and change management standard
- Supplier-defined controls
- Configuration and change management approach
- The entirety of the service is 'as code' and is provisioned using a CI/CD pipeline. As the service has two AWS accounts the pipeline's merge policy acts to keep the environment's configuration and source code in lock step with one another - where a change is first tested in a staging branch, deployed to the staging environment before being merged in to the production branch and deployed to production. In order to merge changes into upper branches a peer review is conducted. In addition all releases are packaged as Docker images, which are scanned prior to deployment for known vulnerabilities.
- Vulnerability management type
- Supplier-defined controls
- Vulnerability management approach
- All software published to the service is originated from our private git repositories and compiled as Docker images on a per environment basis. These are subject to vulnerability scans when being pushed into deployment.
- Protective monitoring type
- Supplier-defined controls
- Protective monitoring approach
-
All of our customer’s cloud instances (configured as exclusive accounts on our cloud platform) are configured to ship logs for any suspected or malicious activity detected in the service. These are a wide range of triggers that are designed to alert of unusual activity and cover scenarios such as:
Denial of service
Network port sweep
Port probing
Password brute force
Root credential usage
Policy disabling
Logs of these events are centralised in a separate operations account whereby upon the receipt of abnormal behaviour we would investigate and either triage the symptom, close a vulnerability or implement a temporary workaround. - Incident management type
- Supplier-defined controls
- Incident management approach
-
All service endpoints are monitored and in the event of an availability check reporting as down we would raise a ticket and investigate. In addition we provide customers of the service a customer service and ticket portal where they can also raise incidents in the event the service is unavailable.
Our standard SLA Incident Management support service Monday to Friday (excluding UK Public Holidays) between 08.00 and 18.00
Our incident prioritisation matrix is available in our SLA.
Escalation of an incident would be conducted via the Customer Success Manager allocated to the customer's account.
Secure development
- Approach to secure software development best practice
- Conforms to a recognised standard, but self-assessed
Public sector networks
- Connection to public sector networks
- No
Social Value
- Covid-19 recovery
-
Covid-19 recovery
As outlined in the government’s ‘Build Back Better’ policy paper published in March this year, innovation will be a key part of the UK’s recovery following the Covid-19 pandemic.
This view is supported by the OECD who declared “Data-driven innovation forms a key pillar in 21st century sources of growth.“ This will be enabled by utilising the massive amounts of data available. “These large data sets are becoming a core asset in the economy, fostering new industries, processes and products and creating significant competitive advantages.”
Pro-Lar is a suite of integratable AI/ML services aimed at organisations looking to innovate by generating actionable customer insights and increasing operational efficiency. These include, but are not limited to, recommender systems, churn prediction models, customer segmentation models and data disambiguation services, as well as modules which recommend intervention strategies for our churn prediction service.
With Pro-Lar, AI-driven decision making can be applied to a wide range of use-cases in the public and third sector. For example, we have applied Pro-Lar to answer questions such as which schools might best-serve disadvantaged students on a case-by-case basis, which charities would best-align with public outreach programmes sponsored by companies in the private sector and what the anticipated cost of maintenance might be for social housing estates in the next year. Pro-Lar could be used to help promote community engagement, match volunteers to opportunities, help young people find apprenticeships or understand how users interact with a charity’s website. A common outcome is the generation of actionable insights and increased user engagement.
Due to the modular design of Pro-Lar, the product can be tailored to match the requirements of the use-case. Pivigo will happily sit down with you to identify exactly where Pro-Lar could help deliver a better service to your customers and better insights for you.
Pricing
- Price
- £5,000 a unit a month
- Discount for educational organisations
- Yes
- Free trial available
- No