TalentUp salary platform FAQs

This knowledge base is a guide to help you understand how TalentUp works, what data we collect, how we validate our models, and how we publish salaries on our platform.

1. What is TalentUp?

TalentUp is provider of the world’s first truly global salary platform which uses machine learning model to make salary predictions. This means our system continuously learns and improves as we feed more data into it. The dataset we use comes from hundreds of sources specific to the job & talent market, such as job boards, public salary surveys, specific websites publishing salaries, and company data; We have harvested over +250M profiles +65M job posts +23M salaries +7M companies.

What is our methodology? What are our data sources?

How we work in 5 simple steps:

I. Collect data

We collect data from hundreds of sources mainly Job boards, social networks, public salary surveys, and company sites publishing salaries. We record a number of attributes such as job title, years of experience, seniority level, job descriptions, number of jobs posted, number of professionals available, and compensation packages being offered for hundreds of job profiles. To give you some examples of data sources we use:

Job boards: Indeed, Monster

Salary sites: Buffer, Levels.fyi

Surveys: Ask A Manager Survey, Recruiter Salaries

Social networks: Linkedin, Xing

II. Deduplicate and normalize data

The dataset is first processed by removing duplicates followed by normalization so that it can be modelled.

III. Split dataset for training & testing

This dataset is then split into training and testing sets. The testing sets are used for validating various models we experiment with, while training sets are used by the system to learn and improve from experience.

IV. Create decision tree models

We use regression models to map relations between cities, countries, roles, and seniority levels. This enables us to predict accurate salaries even with small sample size. We validate the various models to ensure accuracy greater than 85%.

V. Predict salaries

Once the models are validated the system makes salary predictions. Finally, these salaries are published on the platform.

How do we get the seniority levels?

currently, we get the seniority level from the job description and the title, we use different filters and steps to validate it (like salary must be in concordance with the seniority requested, or the seniority level/years experience have to be similar to other job offers published)

How often is the data updated?

It’s updated every 2 weeks, we use a window of 12 months and discard data older than 12 months.

Why does the data show an updated date of more than 2 weeks?

The system usually updates every two weeks but in case the script breaks, then the salary ranges that were last calculated are shown. This happens when we are updating the program script to add new features to the platform.

Is it possible to export the salaries via excel?

Yes, you can export the data in a CSV format from the Salaries section for individual roles, and locations.

Is it possible to export data for multiple roles in multiple locations all-at-once?

Yes, you can export data in a CSV format for multiple roles and locations in the Salary overview section. Here is a short video showing how: Loom | Free Screen & Video Recording Software | Loom