Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/HelenDiMo/TinderJob/llms.txt

Use this file to discover all available pages before exploring further.

The Probabilidad Condicional tab takes the market data one step further than descriptive statistics. Rather than simply reporting averages, it answers three specific business questions that DataTalent consultants and candidates ask in practice: how likely am I to earn above the market median given my current experience level? Which type of company gives me the best chance of working fully remote? And which Spanish cities are genuinely flexible versus merely claiming to be? Each chart models one of these questions as a conditional probability P(A|B), making the answers both rigorous and immediately actionable.

​
Background: What is P(A|B)?

P(A|B) is the probability of event A occurring given that condition B is already true. It is computed as: 
P(A|B) = P(A ∩ B) / P(B)
In the TinderJob context: what is the probability of a favorable outcome (high salary, remote work, flexible modality) given a candidate’s current situation (experience level, company type, city of the offer)? Framing market data as conditional probabilities transforms raw counts into decision-relevant guidance. A consultant can tell a junior candidate not just “seniors earn more” but “your probability of exceeding the market median triples when you reach Senior level.”

​
Correlation Heatmap (Prerequisite)

Before the three probability charts, the tab renders a correlation heatmap of three continuous variables from the DS Salaries dataset: salary_in_eur, remote_ratio, and work_year.
Variable pairCorrelation
Salary ↔ Remote ratio0.13 (weak positive)
Salary ↔ Yearweak positive
Remote ratio ↔ Yearweak positive (max ~0.17)
All correlations are weak (maximum absolute value ≈ 0.17). This is a critical finding: work modality does not determine salary. The assumption that remote jobs pay less (or more) is not supported by this data. The primary salary driver — as confirmed throughout the salary analysis tab — is experience level, not where or when someone works.

​
Scenario 1 — P(High Salary | Experience Level)

Definition: P(salary > global median | experience level) The global salary median from the DS Salaries dataset is €93,444. For each experience level, the chart computes what fraction of workers at that level earn above this threshold.
LevelP(Salary > €93,444)
Entry-level (Junior)11.4%
Mid-level (Semi-senior)~35–40%
Senior73.2%
Executive / Director>90%
A 50% reference line is drawn on the chart — levels above it have better-than-even odds of exceeding the median. Key insight: the Senior threshold is the critical inflection point. At Junior level, a candidate has a 1-in-9 chance of earning above the median. At Senior level, that probability rises to 3-in-4 — nearly tripling at the Mid-senior → Senior transition. For DataTalent’s reskilling programs, this provides a clear financial argument: reaching Senior level is not just a career milestone, it is a probability-shifting event.

​
Scenario 2 — P(Remote Work | Company Size)

Definition: P(remote_ratio == 100 | company_size) For each company size category, the chart computes the fraction of roles that are 100% remote (not hybrid, not partial — fully remote).
Company SizeP(100% Remote)
Pequeña / Small (<50)moderate
Mediana / Medium (50–250)69.3%
Grande / Large (>250)53.5%
A 50% reference line is drawn — both medium and large companies cross it; small companies fall below. Insight: medium-sized companies (50–250 employees) are the strongest segment for candidates who prioritize 100% remote work, with a probability of 69.3% — substantially higher than large enterprises (53.5%). Candidates who make remote work a non-negotiable should focus their applications on mid-sized tech companies rather than large corporations or startups.

​
Scenario 3 — P(Flexible Work | City) — Tecnoempleo Spain

Definition: P(modalidad ∈ | city), computed only for cities with at least 5 offers in the dataset. This chart uses the Tecnoempleo Spanish dataset (not DS Salaries) and shows the top 15 cities by flexibility probability, sorted descending. A 50% reference line marks the midpoint. Notable results:
CityFlexibility Probability
Alcobendas86%
Almería76%
Madrid44%
Barcelona45%
Counterintuitive insight: Madrid and Barcelona concentrate the largest absolute number of tech offers in Spain, yet their flexibility probability (44–45%) falls below the 50% threshold. Smaller cities like Alcobendas and Almería — while offering fewer total positions — have a much higher share of flexible roles. The practical implication for candidates in cities like Sevilla or Zaragoza is not to limit their search to local postings. Given that over half of defined-modality offers are flexible nationwide, candidates in secondary cities should actively target remote-first companies headquartered elsewhere, particularly in Madrid or Barcelona where the volume is highest even if the flexibility rate is lower.

Build docs developers (and LLMs) love

Get started for freeTalk to us