> ## Documentation Index
> Fetch the complete documentation index at: https://help.yapamar.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Overview

## **What Yapamar Does**

Yapamar is a **Marketing Mix Modelling (MMM) platform**. In plain language, it answers a question that every company with a marketing budget asks:

> "We spent money on Facebook ads, Google ads, TV, radio, and other channels. Which of those actually drove sales — and by how much?"

Traditional marketing analytics can tell you how many people clicked an ad. Yapamar goes further: it uses statistical modelling to estimate **how much each marketing channel actually contributed to sales**, even for channels like TV and radio where clicks don't exist.

The platform collects marketing spend data from advertising platforms (Google Ads, Meta/Facebook, TikTok, Snapchat, LinkedIn, YouTube), combines it with external economic signals (unemployment rates and consumer confidence), runs Bayesian statistical models on that data, and presents the results through an interactive web dashboard.

## **What Problem It Solves**

Marketing teams typically face these challenges:

* **Attribution confusion**: Digital platforms each claim credit for the same sale. Facebook says their ad caused a purchase; Google says their ad did. Without an independent model, there's no way to know the real picture.
* **Offline channels are invisible**: TV, radio, print and outdoor advertising have no click tracking. Companies spend large budgets on these channels with little ability to measure their actual impact.
* **Budget allocation is guesswork**: Without knowing which channels actually work, marketing teams allocate budgets based on intuition, history, or vendor recommendations — not evidence.

Yapamar solves these by building a **statistical model** that looks at the relationship between marketing spending across all channels and actual business outcomes (sales, conversions, registrations) over time. The model separates out what would have happened anyway (the "base" sales) from what each marketing channel contributed (the "incremental" effect).

## **A Real-World Analogy**

Imagine you own a lemonade stand. Sales change from week to week: sometimes people buy more, sometimes less.

Many different factors influence sales. Some of them are under your control: for example, you put up a bright new sign, run online advertising, hand out flyers, or place an ad in the local newspaper. But there are also factors you cannot control:

* During holidays, more people are out and about, so sales tend to increase (holidays effect).
* People buy lemonade more often in the summer than in the winter (seasonality effect).
* Weekends typically bring more customers than weekdays (weekday effect).
* When consumers feel confident about their financial situation, they are more willing to spend money (consumer confidence index).
* When unemployment rises, people may cut back on spending and buy less (unemployment rate).

Now imagine that in the same week you put up a new sign, launched an advertising campaign, and happened to benefit from a long holiday weekend. Looking at sales alone, it would be difficult to determine which factor actually drove the increase.

Yapamar analyzes historical data and estimates the contribution of each factor to overall performance. The model evaluates how many sales were generated by advertising, the new sign, and the newspaper ad; how much can be explained by holidays and seasonality; and how much is related to broader economic conditions and consumer behavior.

This makes it possible to understand which factors truly drive sales and where future budget investments will have the greatest impact. If growth is primarily driven by your marketing activities, those efforts can be scaled. If sales increased mainly because of holidays or seasonal patterns, you can avoid mistakenly attributing all of that success to advertising.