About Dataset

LeadForge: Synthetic B2B Lead Scoring Dataset (`leadforge-lead-scoring-v1`)

A relational, reproducible, three-tier synthetic CRM dataset family for teaching lead scoring at scale. Generated by leadforge, an open-source Python framework for synthetic CRM/funnel data. The framework version is decoupled from the dataset version: the package stays at 1.x; the dataset is published under the explicit …-v1 tag.

Why lead scoring matters in 2024–2026

Mid-market SaaS vendors entered 2024–2026 with growth slowing and customer-acquisition costs rising[^macro], so predicting which leads convert within a fixed window has moved from a marketing nicety to a survival skill. This dataset teaches that skill on a relational substrate, with the realistic confusions (snapshot-window discipline, leakage traps, channel signal weaker than vendor blogs imply) that students will hit when they finally get hands on real CRM data.

[^macro]: Macroeconomic framing summarised in docs/external_review/summaries/gemini_v2_summary.md (median public-SaaS growth 30%→25% from 2023 to 2025; New CAC Ratio rose materially in 2024).

What's inside

release/
├── intro/ intermediate/ advanced/    # student_public bundles, one per difficulty tier
│   ├── manifest.json                 # provenance + file hashes
│   ├── metrics.json                  # per-tier headline metrics (medians + spreads)
│   ├── dataset_card.md               # auto-rendered per-bundle card
│   ├── feature_dictionary.csv        # authoritative column spec
│   ├── lead_scoring.csv              # flat convenience CSV (all splits)
│   ├── tables/*.parquet              # 7 snapshot-safe relational tables
│   └── tasks/converted_within_90_days/{train,valid,test}.parquet
├── intermediate_instructor/          # research companion: full-horizon tables + metadata/
├── docs/                             # vendored DGP / leakage / break-me docs (agent-readable)
├── notebooks/                        # 01 baseline · 02 relational · 03 leakage · 04 calibration
├── metrics.json                      # top-level cross-tier metrics summary
├── claims_register.{md,json}         # claims → backing-artifact map (agent-readable)
└── validation/                       # validation_report.{json,md} + figures

student_public bundles ship the snapshot-safe relational view; research_instructor companions ship the full-horizon view plus the hidden causal structure (DAG, latent registry, mechanism summary) under metadata/. The full layout is documented in each bundle's manifest.json.

Agent-reviewable artifacts

The published bundle is self-contained for AI review and offline auditing — every numeric / structural claim on this page can be verified without following an external link:

metrics.json (root) + <tier>/metrics.json — deterministic JSON view of the headline LR AUC / AP / P@100 / Brier / conversion rate / cohort-shift / cross-tier-ordering medians, with JSON-path back-references to validation/validation_report.json (the source of truth).
claims_register.{md,json} — every numerical or structural claim on this page paired with the artifact and path that backs it. Rendered from claims_register_source.yaml by scripts/build_claims_register.py.
docs/ — vendored copies of generation_method.md, channel_signal_audit.md, break_me_guide.md, feature_dictionary.md, v1_acceptance_gates_bands.yaml, v2_decision_log.md, plus a hand-authored relational_table_schemas.csv documenting every column of every relational table. These match the GitHub-blob links cited below but ship inside the bundle so a reviewer never needs network access.
<tier>/manifest.json — SHA-256 hash for every file plus the full redaction contract (structural_redactions.columns, omitted_tables, relational_snapshot_safe, snapshot_day).
Kaggle / HuggingFace preview pages additionally inject a schema.org/Dataset JSON-LD block in their <head> for agent ingestion without HTML parsing.

Quick start

# Flat CSV
df = pd.read_csv("intermediate/lead_scoring.csv")

# Parquet task splits (recommended)
train = pd.read_parquet("intermediate/tasks/converted_within_90_days/train.parquet")
test  = pd.read_parquet("intermediate/tasks/converted_within_90_days/test.parquet")

# Relational tables (feature engineering — example)
leads   = pd.read_parquet("intermediate/tables/leads.parquet")
touches = pd.read_parquet("intermediate/tables/touches.parquet")
my_touch_count = (
    touches.groupby("lead_id").size().rename("my_touch_count").reset_index()
)
features = leads.merge(my_touch_count, on="lead_id", how="left")

# Reproduce from source
# pip install leadforge
# leadforge generate --recipe b2b_saas_procurement_v1 --seed 42 \
#                    --mode student_public --difficulty intermediate --out my_bundle

The label converted_within_90_days resolves over a 90-day window; engagement features (touch_count, session_count, etc.) are computed strictly over events on days [0, 30]. The deliberate exception is total_touches_all, the leakage trap — flagged leakage_risk=True in feature_dictionary.csv. Drop it from your feature set unless you're demonstrating leakage detection.

Dataset summary

	Intro	Intermediate	Advanced
Leads	5,000	5,000	5,000
Accounts	1,500	1,500	1,500
Contacts	4,200	4,200	4,200
Snapshot columns	32 / 34*	32 / 34*	32 / 34*
Target	`converted_within_90_days`	`converted_within_90_days`	`converted_within_90_days`
Conversion rate (acceptance band, gate G7.*)	24–61%	12–31%	4–12%
Conversion rate (observed median, seeds 42–46)	42.67%	21.60%	8.40%
Signal strength	0.90	0.70	0.50
Noise scale	0.10	0.30	0.55
Missing rate	2%	8%	18%

* student_public / research_instructor. Difficulty is modulated by the simulation engine — signal strength on latent-trait weights, Gaussian noise on float features, MCAR missingness, outlier rate — not post-hoc label flipping. The acceptance band is the recipe gate's tolerance window (v1_acceptance_gates_bands.yaml G7.*), not the achievable range — observed five-seed spreads sit comfortably inside the band.

The scenario

Veridian Technologies is a fictional Series B startup (Austin, US) selling Veridian Procure, a procurement / AP automation SaaS, to mid-market firms (200–2,000 employees) in the US and UK. The funnel runs through inbound marketing (45%), SDR outbound (35%), and partner referrals (20%); four personas drive deals (VP Finance, AP Manager, IT Director, Procurement Manager). Task: predict whether a lead converts (closed_won) within 90 days. ACV bands are $18k–$120k. See docs/release/generation_method.md for the full DGP, and the deeper "what's modelled / approximate / not modelled" breakdown that this README only summarises.

Public vs instructor: what's redacted

Filtering happens during rendering, not during simulation. The redaction contract is single-sourced in leadforge/validation/leakage_probes.py; the snapshot-safe writer and the validator import the same constants, so they cannot drift apart.

Source-of-truth constant	Public bundle treatment
`BANNED_LEAD_COLUMNS = ("converted_within_90_days", "conversion_timestamp")`	Dropped from `tables/leads.parquet`
`BANNED_OPP_COLUMNS = ("close_outcome", "closed_at")`	Dropped from `tables/opportunities.parquet`
`BANNED_TABLES = ("customers", "subscriptions")`	Omitted from public bundles
`SNAPSHOT_FILTERED_TABLES` (touches, sessions, sales_activities, opportunities)	Filtered per-lead by `lead_created_at + snapshot_day`
Snapshot redaction (`current_stage`, `is_sql`)	Stripped from `tasks/` splits and `tables/leads.parquet`
`total_touches_all` (deliberate trap)	Retained in both modes; flagged `leakage_risk=True`

Each bundle's manifest.json records relational_snapshot_safe, redacted_columns, and snapshot_day, so the bundle is self-describing.

Calibration

Every realism / calibration / difficulty claim in this README is backed by validation/validation_report.md, regenerated by scripts/validate_release_candidate.py with bands declared in docs/release/v1_acceptance_gates_bands.yaml. Headline cross-seed medians (seeds 42–46):

Tier	LR AUC	AP	P@100	Brier
intro	0.879	0.761	0.80	0.130
intermediate	0.886	0.575	0.59	0.110
advanced	0.886	0.351	0.34	0.061

AP, P@100, conversion-rate, and lift orderings hold across the intended difficulty axis (intro > intermediate > advanced).

Intended uses

Teaching baseline lead-scoring on a flat snapshot.
Teaching relational feature engineering against snapshot-safe tables.
Teaching leakage detection (the total_touches_all trap is designed to be discoverable).
Teaching calibration, lift, P@K, value-aware ranking (expected_acv × P(convert)), and cohort-shift evaluation.
Comparing model families under a controlled DGP.

Out-of-scope uses

Production lead scoring. The company, product, and customers are fictional.
Vendor benchmarking / paper baselines. Difficulty tiers are calibrated for pedagogy, not cross-paper comparability.
Causal-inference research that requires recovery of the true DGP. The instructor companion exposes the hidden graph for teaching, not designed counterfactuals.
Demographic / fairness research. v1 does not model protected attributes.

Known limitations

Difficulty signal on raw AUC is flat. LR AUC is ~0.88 across every tier. Difficulty is visible in AP, P@K, Brier, and value capture. Treat AUC as a sanity check, not a difficulty signal.
GBM does not consistently beat LR (gate G7.4.4). GBM−LR AUC delta is slightly negative in every tier (intro −0.0045, intermediate −0.0072, advanced −0.0133); v1's snapshot is dominated by linear features. v2 will inject non-linear interactions in the simulator.
Channel signal is weak. Per docs/release/channel_signal_audit.md, out-of-sample univariate AUC of lead_source is ≈0.50–0.52 across all tiers and the per-channel rate spread is ≤0.05. The simulator does not encode channel-conditional probabilities; channel-conditional encoding is post-v1 work.
Cohort-shift degradation is small. v1 has no time-of-year drift baked in; the cohort-shift gate (G6.4) is informational and will bite in v2.

Composition

Entities. Accounts, contacts, leads, touches, sessions, sales_activities, opportunities (public); plus customers and subscriptions (instructor only). Per-row counts per bundle live in manifest.json.
Features. 32 public columns grouped by analytical role in docs/release/feature_dictionary.md; the per-bundle feature_dictionary.csv is the authoritative machine-readable spec.
Label. converted_within_90_days (boolean), event-derived from the simulator. Never sampled directly.
Splits. 70/15/15 train/valid/test, deterministic given seed; recorded in tasks/converted_within_90_days/task_manifest.json. Group-leakage warning: the splitter is keyed on lead_id only, not on account_id or contact_id. On the as-shipped intermediate bundle, 518 of 557 test accounts (≈93 %) also appear in train; the contact-level overlap is similar in magnitude. A flat baseline trained on the random split rides account-level signal across the split boundary. For a generalisation-faithful number, retrain with GroupKFold(account_id) (or contact_id) and report both — see break_me_guide.md §5 for the detection recipe.
Provenance. Recipe b2b_saas_procurement_v1, seed 42, package version stamped in manifest.json.

Maintenance, adversarial framing, license

We want the dataset to be broken. The break-me guide catalogues nine adversarial patterns to look for (leakage, split contamination, ranking inversions, calibration drift) with worked-example pointers back into the notebooks. Issue templates ship under .github/ISSUE_TEMPLATE/: a breakage report form for findings on the bundle itself, and a realism feedback form for distributional critiques. Accepted findings are logged in docs/release/v2_decision_log.md. File issues at leadforge-dev/leadforge; PRs welcome.

Field	Value
Generator	leadforge `1.0.0+`
Recipe	`b2b_saas_procurement_v1`
Canonical seed	42 (cross-seed sweep: 42–46)
Bundle schema version	5
Format	Parquet (canonical) + CSV (convenience)
License	MIT — see LICENSE

Verify integrity with leadforge validate <bundle_dir>; every file is hashed in manifest.json.

Objective

This deliberately fake release is large enough to exercise row previews, file downloads, metadata, and review copy before a real upload to Kaggle.

Do an EDA and try to predict which socks and laundry conditions achieve suspiciously stable pair success.

LeadForge Lead Scoring v1 — Advanced

Aaccount_id Link to Organization	123industry Industry	123region Region	123employee_band Employee Band	123estimated_revenue_band Estimated Revenue Band	123process_maturity_band Process Maturity Band	Acontact_id Contact Id	123role_function Role Function	123seniority Seniority	123buyer_role Buyer Role	Alead_id Lead Id	123lead_created_at Lead Created At	123lead_source Lead Source	123first_touch_channel First Touch Channel	123touch_count Touch Count	123inbound_touch_count Inbound Touch Count	123outbound_touch_count Outbound Touch Count	123session_count Session Count	123pricing_page_views Pricing Page Views	123demo_page_views Demo Page Views	123total_session_duration_seconds Total Session Duration Seconds	123touches_week_1 Touches Week 1	123touches_last_7_days Touches Last 7 Days	123days_since_first_touch Days Since First Touch	123activity_count Activity Count	123days_since_last_touch Days Since Last Touch	123opportunity_created Opportunity Created	123has_open_opportunity Has Open Opportunity	123opportunity_estimated_acv Opportunity Estimated Acv	123expected_acv Expected Acv	123total_touches_all Total Touches All	123converted_within_90_days Converted Within 90 Days
136unique values	logistics 18% logistics 8% Other (3,533) 79%	UK 17% UK 7% Other (3,250) 80%	200-499 16% 500-999 6% Other (2,967) 81%	$50M-$200M 15% $10M-$50M 5% Other (2,684) 82%	low 14% high 4% Other (2,401) 83%	cnt_001124 13% cnt_003354 3% Other (2,118) 84%	procurement_manager 12% it_director 2% Other (1,835) 85%	vp 11% c_suite 2% Other (1,552) 86%	end_user 10% technical_evaluator 2% Other (1,269) 87%	lead_004250 9% lead_001565 2% Other (986) 88%	2024-01-08 8% 2024-01-01 2% Other (703) 89%	inbound_marketing 7% inbound_marketing 2% Other (420) 90%	inbound_marketing 6% inbound_marketing 2% Other (137) 91%	102unique values	68unique values	102unique values	85unique values	1.0 6% 4.0 2% Other (1) 94%	0.0 6% 0.0 2% Other (1) 94%	136unique values	1.0 6% 4.0 2% Other (1) 94%	2.0 6% 1.0 2% Other (1) 94%	24.08619850861116 6% 30.62883305317309 2% Other (1) 94%	68unique values	-3.5747144539187232 6% 1.8952519188233432 2% Other (1) 94%	True 6% True 2% Other (1) 94%	True 6% True 2% Other (1) 94%	37710.42551803246 6% 52804.112720196485 2% Other (1) 94%	-10645.128882835355 6% 80317.28475907192 2% Other (1) 94%	51unique values	False 6% False 2% Other (1) 94%
acct_000773	logistics	UK	200-499	$50M-$200M	low	cnt_001124	procurement_manager	vp	end_user	lead_004250	2024-01-08	inbound_marketing	inbound_marketing	8.0	8.0	0.0	1.0	1.0	0.0	484.0	1.0		24.08619850861116	6.0	-3.5747144539187232	True	True	37710.42551803246	-10645.128882835355		False
acct_000043	logistics	UK	500-999	$10M-$50M	high	cnt_003354	it_director	c_suite	technical_evaluator	lead_001565	2024-01-01	inbound_marketing	inbound_marketing	9.0	9.0	0.0	3.0	4.0		900.0	4.0		30.62883305317309		1.8952519188233432	True	True	52804.112720196485	80317.28475907192		False
acct_000319	logistics	US	200-499	$1M-$10M	medium	cnt_000537	ap_manager	director	champion	lead_002296	2024-01-05	partner_referral	partner_referral	9.0	0.0	9.0	4.0	0.0	0.0	1065.0	4.0	2.0	27.053826214825193		3.2322809610775023	False	False		15778.446526640288	17.0	False
acct_000476	healthcare_non_clinical	US	200-499	$10M-$50M	medium	cnt_001478	ap_manager	director	champion	lead_003320	2024-01-29	inbound_marketing	inbound_marketing	13.0	13.0	0.0	4.0		0.0	1381.0	1.0	1.0	22.61679442790949	4.0	-4.398843829294206	True	True	-1312.8841795232147	-11408.728282716547	14.0	False
acct_000243	manufacturing	US	1000-1999	$10M-$50M	low	cnt_000276	vp_finance	individual_contributor	economic_buyer	lead_001192	2024-01-01	sdr_outbound	sdr_outbound	8.0	0.0	8.0	2.0	1.0	0.0	1128.0			32.29311067265875	1.0	3.5385907968992516	True	True	47876.648993836	35049.85592930211		False
acct_000353	manufacturing	UK	2000+	$1M-$10M	medium	cnt_002665	procurement_manager	vp	end_user	lead_000123	2024-01-27	sdr_outbound	sdr_outbound	6.0	0.0	6.0	2.0	0.0	0.0	150.0	4.0	2.0	26.215262450130034	3.0	3.1313429432706332	False	False		23551.864433039216		False
acct_000029	healthcare_non_clinical	US	500-999	$10M-$50M	low	cnt_001377	procurement_manager	individual_contributor	end_user	lead_001076	2024-01-18	sdr_outbound	sdr_outbound	11.0	0.0	11.0	0.0	0.0	0.0	0.0	5.0	2.0				False	False		75080.37802229391	14.0	False
acct_001411	professional_services	US	200-499	$10M-$50M	high	cnt_002913	vp_finance	c_suite	economic_buyer	lead_001584	2024-01-09	sdr_outbound	sdr_outbound	3.0	0.0	3.0	1.0		0.0	234.0			28.188032773479	6.0	3.2455395630901305	True	True	20430.54627729372	-17325.35698486596	13.0	False

LeadForge Lead Scoring v1 — Advanced

About Dataset

LeadForge: Synthetic B2B Lead Scoring Dataset (`leadforge-lead-scoring-v1`)

Why lead scoring matters in 2024–2026

What's inside

Agent-reviewable artifacts

Quick start

Dataset summary

The scenario

Public vs instructor: what's redacted

Calibration

Intended uses

Out-of-scope uses

Known limitations

Composition

Maintenance, adversarial framing, license

Objective

lead_scoring.csv (1353 KB)

About this file

Metadata

Activity Overview

LeadForge Lead Scoring v1 — Advanced

About Dataset

LeadForge: Synthetic B2B Lead Scoring Dataset (leadforge-lead-scoring-v1)

Why lead scoring matters in 2024–2026

What's inside

Agent-reviewable artifacts

Quick start

Dataset summary

The scenario

Public vs instructor: what's redacted

Calibration

Intended uses

Out-of-scope uses

Known limitations

Composition

Maintenance, adversarial framing, license

Objective

About this file

See what others are saying about this dataset

What have you used this dataset for?

How would you describe this dataset?

Metadata

Activity Overview

LeadForge: Synthetic B2B Lead Scoring Dataset (`leadforge-lead-scoring-v1`)