Request a demo
MODULE 01 · PRINT RUN — FIRST PRINT RUN

The right print-run decision, grounded in real comparable titles.

Assess the potential and decide on the optimal print run for your new releases.

For whom: Editorial director, Distribution director · Print buyer, Product manager
Request a Print Run demo
V

THE MYSTERIOUS ISLAND

VERNE-J
ISBN :978-2-815-15925-5€6.90
BRAND
Stellaire Publishing
DIVISION
Children & Picture Books
COLLECTION
Collection ABC
SERIES
One-shot
PRINT RUN PROPOSAL Reset
BASE
7318
WITH ROLLOUT
6749
ROLLOUT: 6,464
WITH TREND
6774
Trend: 6,502

Delivery info

  • Delivery04/23/2026
  • Today05/03/2026
  • Release date05/18/2026

Influence parameters

  • Catalog densityStrong brake (-5)
  • Product featuresSignificant boost (+4)
  • Comparable titles performanceSignificant brake (-4)
  • Author performanceModerate boost (+3)
  • Theme dynamicsMild brake (-2)

Author history (3 years)

  • V
    Twenty Thousand Leagues Under the Sea
    VERNE-J
    3M6M12M1st print
    Outflow1,2733,3139,30014,499
    Net sales8404,0498,094
  • V
    Journey to the Center of the Earth
    VERNE-J
    3M6M12M1st print
    Outflow1,7885,9373,13014,405
    Net sales2,3934,9437,645
  • V
    From the Earth to the Moon
    VERNE-J
    3M6M12M1st print
    Outflow9622,8146,10211,802
    Net sales1,1213,2205,488

Keywords

FictionBestsellerNew releaseBookEdition

Sanity Score

Assess input data quality & volatility

89
%
SANITY

Summary

In this thrilling new volume, VERNE-J takes us on an epic adventure full of twists. Characters evolve and transform across the pages, offering readers an immersive and memorable experience.

The problem

Decide a print run before publication. With very little certain information.

Every new title needs a print-run decision: how many copies to print? This decision is made before publication, on the basis of very little certain information. Publishers traditionally rely on experience and informal comparisons with past titles.

DemandSens formalises and automates this comparison through the notion of comparable titles: a past title, comparable to the new one, used as the basis for calculation.

Feature 01 · Comparables engine
shared with DS Agent §04

Identify truly comparable titles, across the entire catalogue.

For every new title, the engine computes a similarity distance against all titles in the catalogue (group, same publisher, external publishers), and surfaces the closest ones as candidate references. Automatic or manual selection, up to 3 references kept per title.

Principle · Content-based filtering
same publisher in groupother publisher in groupexternal publisher
Output: a ranking scored by similarity distance, with provenance shown.
Inputs · 3 signal families
Structural metadata
AuthorProduct typeClassification (Thema · CLIL · BISAC)Publication datePublisher · CollectionFormat · PaginationPrice
Content & description
ExcerptSummaryKeywordsTheme
Market signals
Author's historical performanceCollection dynamicsSeasonality
Auto selection (top-K) Manual selection Reference history sheet Distance shown per candidate
Feature 02 · Machine Learning engine
Core foundation

200+ parameters. Three specialised engines. Continuously retrained.

The DemandSens ML engine consumes more than 200 parameters, a large share of which is built by DemandSens as proprietary derived features (not just raw inputs). The model is versioned, retrained and redeployed automatically, with no intervention on the publisher's side.

Pipeline · 5 stages
ÉTAPE 01
Ingest
Extract · Merge · Clean
ÉTAPE 02
Prepare
Enrich · Standardize · Cluster
ÉTAPE 03
Model
Train · Optimize · Validate
ÉTAPE 04
Deploy
Ensemble · Validate
ÉTAPE 05
Expose
REST API · Run · Maintain
Three specialised engines · powered by the pipeline
Recommendation engine
Detect comparable titles
↑ see Feature 01
Classification engine
First estimate of commercial potential
→ feeds the scenarios
Regression engine
Refined estimate of quantitative potential
→ produces the numerical recommendation
200+
parameters consumed
~70%
DemandSens-built features
auto
retraining & redeployment
3
specialised engines exposed via API
Feature 03 · Module core

Three scenarios, three commercial hypotheses.

The model produces three distinct forecasts, matching three hypotheses. The publisher picks the one matching their moment in the cycle.

SCÉNARIO 01
Baseline scenario
Forecast without commercial objectives
WHEN TO USE IT
Neutral starting point, "natural market" view
SCÉNARIO 02
With commercial objectives
Includes commitments from sales teams
WHEN TO USE IT
When KAMs have already quantified their commitments
SCÉNARIO 03
With trend
Includes current market dynamics (uptrend or downtrend)
WHEN TO USE IT
Mid-cycle, to readjust
Publisher objectives · Generosity dial

The engine integrates your objectives. You stay in control.

Whatever the scenario, the publisher sets two objectives that drive the generosity of the print-run proposal. These objectives are set per division, collection or series — the publisher autonomously adjusts the cursor between unsold risk and stockout risk, according to risk appetite.

Objective 01
Sales window to cover
Over what duration must the initial print run hold? The longer the period, the more generous the proposed print run.
3 months
24 months
e.g. long children's series → 18 months · standalone novel → 6 months
Objective 02
Target unsold rate
What unsold rate is acceptable at end of period? The higher it is, the larger the print-run proposal.
5%
30%
e.g. cautious profile → 8 % · aggressive profile (marketing launch) → 22 %
Objective granularity
DivisionCollectionSeries+ title override
Top-down inheritance through the editorial pyramid (see F05).
Risk dial
← unsold
stockout →
The publisher arbitrates both risks themselves, in full autonomy. DemandSens proposes, the publisher calibrates.
Feature 04 · Explainable AI

Quality score. Drivers explained. Decision always human.

Every forecast comes with a reliability score indicating the recommendation's reliability, based on reference relevance and data availability. The influence parameters are explained and weighted: the publisher sees exactly what pulls the forecast up or down.

« The AI recommendation is explainable. The publisher understands why DemandSens recommends a given number. The final decision still belongs to the publisher. »
6 forecast drivers
Author performance
92%
Collection dynamics
78%
Book theme
64%
Sale price
58%
Catalogue density
41%
Series trajectory
87%
Feature 05 · Governance

4-level editorial pyramid. Automatic rule inheritance.

DemandSens organises the catalogue along a 4-level pyramid. Calculation rules are set at the top level (publisher) and inherited automatically downwards. The user only intervenes for collections or series with atypical behaviour.

Result: 100% of titles under rule, with no per-title parameterisation.
Print Run · in one sentence
« The right print-run decision, grounded in real comparable titles — not in intuition. »
« Cut waste without risking stockout. »
« An AI recommendation, but the decision stays yours. »
« All your titles under rule, thanks to editorial pyramid inheritance. »
To be clear

What this module does not do.

It does not decide for the publisher.
It does not replace editorial judgement on a manuscript's value.
It does not predict "hits" — unforeseen events, sudden media buzz.
For whom?
Decision-maker persona · buyer
Editorial director · Distribution director
Cut waste without risking stockout, harmonise rules across imprints.
User persona · operator
Print run lead · Product manager
Decide a print run in minutes, with reliable, explainable comparables.
Next step
See the Print Run module running live, in 30 minutes.
Request a demo
Explore the other modules of the sales cycle
MODULE 02
Allocate
Set your commercial objectives and proceed with allocation.
MODULE 03
Prospect
Drive commercial outreach.
MODULE 04
Budget
Build and simulate your N+1 budget, without overwriting your data.