Quick start

  1. Open the Dashboard. Use the sidebar to access the prediction form.
  2. Fill in game features. Enter pre-launch attributes across the 10 sections (Pricing, Release, Genre, …).
  3. Submit. Click Predict Success to run the ensemble model.
  4. Review. Inspect the predicted owner tier, confidence, class probabilities, and recommendations.

Feature reference

All 48 pre-launch features, grouped by section:

💰 Pricing

Field Label Type Range
price Price (USD) Number 0–200
initialprice Initial Price (USD) Number 0–200
is_free Free to Play? Yes / No 0 / 1

🗓️ Release

Field Label Type Range
release_month Release Month Selection 12 options

🎮 Genre

Field Label Type Range
Action Action Yes / No 0 / 1
Adventure Adventure Yes / No 0 / 1
RPG RPG Yes / No 0 / 1
Strategy Strategy Yes / No 0 / 1
Simulation Simulation Yes / No 0 / 1
Indie Indie Yes / No 0 / 1
Sports Sports Yes / No 0 / 1
Racing Racing Yes / No 0 / 1

🖥️ Platform

Field Label Type Range
platform_windows Windows Yes / No 0 / 1
platform_mac Mac Yes / No 0 / 1
platform_linux Linux Yes / No 0 / 1

🌍 Languages

Field Label Type Range
supported_languages_count Text Languages Supported Number 0–50
full_audio_languages_count Full Audio Languages Supported Number 0–20

🏪 Store Page

Field Label Type Range
screenshot_count Number of Screenshots Number 0–20
has_trailer Has Trailer? Yes / No 0 / 1
trailer_count Number of Trailers Number 0–10
about_length Description Length (chars) Number 0–5000
has_detailed_desc Detailed Description (>500 chars)? Yes / No 0 / 1
has_website Has Official Website? Yes / No 0 / 1
has_support_email Has Support Email? Yes / No 0 / 1

🏢 Developer / Publisher

Field Label Type Range
developer_count Number of Developers Number 1–20
publisher_count Number of Publishers Number 0–10
has_publisher Has Publisher? Yes / No 0 / 1
is_solo_dev Solo Developer? Yes / No 0 / 1
required_age Required Age (0=none) Number 0–18
is_mature_content Mature Content (18+)? Yes / No 0 / 1

🏆 Steam Features

Field Label Type Range
has_achievements Steam Achievements? Yes / No 0 / 1
achievement_count Number of Achievements Number 0–500
has_trading_cards Steam Trading Cards? Yes / No 0 / 1
has_workshop Steam Workshop? Yes / No 0 / 1
has_cloud_save Steam Cloud Save? Yes / No 0 / 1
has_controller_support Controller Support? Yes / No 0 / 1
has_vr_support VR Support? Yes / No 0 / 1
has_in_app_purchases In-App Purchases? Yes / No 0 / 1
has_family_sharing Family Sharing? Yes / No 0 / 1
category_count Total Steam Categories Number 0–15

🏷️ Tags & Community

Field Label Type Range
tag_count Number of Tags Number 0–20
has_multiplayer_tag Has Multiplayer Tag? Yes / No 0 / 1
top_tag_votes_total Top Tag Votes Total Number 0–5000
top_tag_votes_mean Top Tag Votes Mean Number 0–1000
is_multiplayer Multiplayer Game? Yes / No 0 / 1

📦 Packaging & DLC

Field Label Type Range
dlc_count DLC Count Number 0–50
package_count Package Count Number 1–10
sku_count SKU Count Number 1–20

Understanding results

Predicted owner tier

  • Class 0 (≤10K) — Common Indie
  • Class 1 (35K) — Niche
  • Class 2 (75K) — Growing
  • Class 3 (150K) — Established
  • Class 4 (350K) — Popular
  • Class 5 (≥750K) — Breakout Hit

Confidence score

  • 80–100%: very confident
  • 60–79%: moderately confident
  • 40–59%: low confidence (borderline)
  • Below 40%: uncertain (mixed/weak features)

Class probabilities

Predicted probability for each of the 6 classes. The class with the highest probability is the final prediction.

Recommendations

  • Strengths — features currently working in your favor (high positive impact)
  • Improvements — actionable suggestions to lift the predicted tier (driven by SHAP analysis)

Best practices

  • Be accurate. The model is trained on real Steam data; inflated numbers mislead predictions.
  • Pre-launch only. No reviews or playtime — fill only what you can decide before release.
  • Use recommendations. Prioritise high-impact suggestions surfaced by SHAP.
  • Test scenarios. Try with/without publisher, varying pricing, etc., to see what moves the needle.
  • Don't over-optimise. Correlations ≠ causation. Game quality is the ultimate factor.

FAQ

What if I don't have a publisher?
Set has_publisher to 0 and publisher_count to 0. Publisher backing helps but isn't required.
Can I predict for unreleased games?
Yes — the model uses only pre-launch features (pricing, store page, platform support, etc.).
What if some features are unknown?
Use the defaults shown in the form. Leave toggles unchecked (0) for features you don't plan to ship.
Why is my confidence low?
Your features fall in regions where multiple classes overlap. Adjust key drivers (store page quality, pricing, platform reach) and try again.
How accurate is the model?
The ensemble achieves 70.85% accuracy and 0.6211 weighted F1 on the test set. See Model Metrics for details.
Does it work for non-Steam platforms?
No. Trained exclusively on Steam data; predictions for Epic, GOG, or consoles aren't reliable.