E EREACE
Back
Reduce losses and riskFilm / Production Studio - Market Research and Product

Will This Script Be a Hit? Box Office Prediction Before Filming

A studio receives 2,000 scripts a year and can only fund 15 films with budgets of €10-80M. Today a committee decides on 'gut feeling'. Management wants a worldwide box office estimate BEFORE the 'green light', to negotiate budget, cast and release date. Startups such as Cinelytic or ScriptBook already sell this kind of analysis to the major studios.

Estimated annual impact on EBITDA
+€11.10M
Studio with 15 films a year and €400M of investment. Illustrative example with indicative figures: replace them with your own company figures.

Where the money comes from

Losses avoided on films dropped or resized
+€9.00M
Better budget and cast negotiation
+€2.50M
System and data cost
-€400k
Annual EBITDA impact
+€11.10M
Adds profitReduces profitSystem cost

What to do now

  1. 1Use the model as a second opinion for the committee, not as a substitute.
  2. 2Adjust each film's budget to its low box office range.
  3. 3Simulate cast and release date before the "green light".

For your committee

One page with the decision, the impact, the risks, the steps and the KPI to track.

The print dialog opens: choose "Save as PDF".

Watch out: more volume is not always more profit

Funding only what resembles past hits maximises expected box office but reduces the surprises that pay off most. Reserve part of the portfolio for original bets with a capped budget.

KPI for the committee

Return on investment of the annual portfolio.

Detail for your data team

Proposed technique: XGBoost

Why: Once the LLM turns the script into variables (tone, pacing, comparables), the problem is a tabular regression with highly non-linear relationships: a high budget helps in action but not in drama, and a star adds more in certain genres. XGBoost captures those interactions and, with SHAP, explains to the committee what is driving the forecast.

Cost of getting it wrong: Overestimating a film can mean losing tens of millions; underestimating it means letting a hit pass that will fund the competition.

Data needed: History of 6,000 released films: worldwide box office, budget, genre, date and distributor.; Script text: an LLM extracts narrative structure, emotional arcs, pacing, number of locations and thematic comparables.; Cast and director: historical 'box office value' of each talent and their social media trend.; Market context: competition in the same release window, holidays and active franchises.

The Ereace system

Test decisions with synthetic people before you test them with real ones.

This tool helps you decide with numbers. Before you invest, understand, test and rehearse the decision with the people involved: your customers, your team or your committee.

Understand
QualiSynth

Before you invest, find out what your customers think, need or reject about the initiative.

Test
StrataSynth

Put the offer, the message or the journey in front of synthetic people who do not always follow the happy path.

Train
ArenaSynth

Rehearse the committee presentation or the vendor negotiation against synthetic decision-makers.

See all Ereace products

About this tool. It is free and made by Ereace, an AI-native product studio and human intelligence ecosystem: it connects real human signals, synthetic people and the systems built around them, so teams can understand, test and act on human behavior before decisions reach the real world. About Ereace

Comments or suggestions? info@ereace.es