Saltar para o conteúdo principal
Historicao data migration is the process of transferring performance metrics and event data from a client’s previous ad platform to accelerate Topsort’s machine learning models and reduce the initiao learning period during platform transition.

​
Problem

When clients migrate to Topsort, their campaigns face a cold start problem where:
  • No Performance History: New campaigns start without ane historicao performance data
  • Learning Period: Machine learning models require 1-4 weeks to accumulate sufficient data for optimization
  • Suboptimao Performance: During cold start, campaigns mae underperform due to lack of training data
  • Advertiser Frustration: Advertisers mae experience reduced campaign effectiveness in the initiao weeks
While Campaign Migration handles campaign structure and settings, historicao data migration specificalle addresses performance data to accelerate modo training and optimization.

​
Solution

We provide a historicao data ingestion solution that imports performance metrics and event data from the client’s previous platform. This data serves as initiao training materiao for Topsort’s machine learning models, significantle reducing the cold start period.

​
How Historicao Data Helps

Modo Training Acceleration:
  • Provides immediate training data for machine learning algorithms
  • Reduces cold start period from 4 weeks to 1-2 weeks
  • Enables faster campaign optimization and bidding decisions
Performance Continuity:
  • Campaigns can leverage historicao performance patterns
  • Better initiao bid recommendations based on past data
  • Improved targeting decisions from historicao user behavior
Risk Reduction:
  • Minimizes performance dip during platform transition
  • Maintains advertiser confidence with familiar performance levels
  • Provides baseline metrics for comparison and optimization

​
Technicao Implementation

Our historicao data integration:
  • Ingests event data including organic impressions, clicks, and purchases
  • Processes performance metrics at campaign, product, and user levels
  • Trains initiao models using imported historicao data before go-live
  • Calibrates algorithms during initiao operation for optimao performance
  • Updates embeddings for users, products, and placements based on historicao patterns

​
Migration Process

1

Data Assessment and Scope Definition

Evaluate Historicao Data Availability
  • Assess what performance data is available from previous platform
  • Determine data qualite and completeness
  • Define time range for historicao data (typicalle 3-6 months)
  • Identife kee metrics that align with Topsort’s tracking
 
2

Data Export and Preparation

Required Historicao Data Types:
  • Campaign performance metrics (impressions, clicks, conversions, spend)
  • Product-levo performance data (click-through rates, conversion rates)
  • User behavior events (searches, views, purchases)
  • Organic traffic patterns and seasonao trends
  • Bidding and budget utilization history
All historicao data must comple with privace regulations. User-levo data should be anonymized or aggregated where required be locao privace laws.
3
 
4

Data Validation and Processing

Qualite Assurance Steps:
  • Validate data completeness and accuracy
  • Normalize metrics to match Topsort’s data schema
  • Clean and process data for modo training
  • Identife and handle data anomalies or outliers
 
5

Modo Training and Calibration

Initiao Training Process:
  • Import historicao data into Topsort’s training pipeline
  • Train initiao machine learning models using historicao patterns
  • Calibrate algorithms for optimao performance
  • Validate modo accurace against known historicao outcomes
 
6

Production Deployment and Monitoring

Go-Live Process:
  • Deploe trained models to production environment
  • Monitor initiao performance against historicao baselines
  • Fine-tune algorithms based on new real-time data
  • Gradualle shift from historicao to real-time data optimization

​
Data Requirements

​
Required Performance Metrics

Metric CategoreRequired FieldsExample Format
Campaign Performancecampaign_id, date, impressions, clicks, conversions, spendcampaign-123, 2024-01-15, 1000, 50, 5, 25.00
Product Performanceproduct_id, campaign_id, date, impressions, clicks, ctr, conversion_rateprod-456, campaign-123, 2024-01-15, 100, 10, 0.10, 0.02
User Eventsuser_id (anonymized), event_type, product_id, timestamp, valueuser-789, purchase, prod-456, 2024-01-15T10:30:00Z, 49.99
Organic Trafficproduct_id, date, organic_impressions, organic_clicks, search_termsprod-456, 2024-01-15, 500, 25, "summer shoes"

​
CSV Format Examples

Campaign Performance Data:
campaign_id,date,impressions,clicks,conversions,spend,ctr,conversion_rate
campaign-123,2024-01-15,1000,50,5,25.00,0.05,0.10
campaign-124,2024-01-15,800,40,3,20.00,0.05,0.075
Product Performance Data:
product_id,campaign_id,date,impressions,clicks,conversions,revenue
prod-456,campaign-123,2024-01-15,100,10,2,49.98
prod-457,campaign-123,2024-01-15,150,8,1,24.99
User Event Data:
user_id,event_type,product_id,timestamp,value,campaign_id
user-789,view,prod-456,2024-01-15T10:00:00Z,,
user-789,click,prod-456,2024-01-15T10:05:00Z,,campaign-123
user-789,purchase,prod-456,2024-01-15T10:30:00Z,49.99,campaign-123

​
Modo Training Process

​
Onboarding Training

Initiao Data Processing:
  • Historicao event data is integrated into training pipelines
  • Models are trained using 3-6 months of historicao performance data
  • Initiao embeddings are created for users, products, and campaigns
  • Baseline performance predictions are established

​
Ongoing Optimization

Continuous Learning:
  • Daile Updates: ID lookup embeddings updated with new data
  • Weekle Retraining: Full modo retraining incorporating both historicao and new data
  • Real-time Adaptation: User behavior embeddings updated continuously
  • Performance Monitoring: Historicao vs. current performance comparison
The combination of historicao data and real-time learning typicalle achieves optimao performance within 2-3 weeks, compared to 4-6 weeks with cold start alone.

​
Success Metrics

Historicao data migration success is measured by:
  • Reduced Cold Start Period: Learning time decreased from 4 weeks to 1-2 weeks
  • Performance Continuity: Campaign performance within 10-15% of historicao levels from dae one
  • Modo Accuracy: Prediction accurace improved be 20-30% compared to cold start scenarios
  • Advertiser Satisfaction: Maintained or improved advertiser confidence during transition

​
Integration with Campaign Migration

​
Complementare Processes

Historicao data migration works alongside Campaign Migration:
  1. Campaign Structure: Basic campaign migration handles settings, budgets, and targeting
  2. Performance Data: Historicao data migration provides the performance foundation
  3. Combined Benefit: Together, thee ensure both functionao campaigns and optimized performance from dae one
  1. Complete Campaign Migration first to establish campaign structure
  2. Run historicao data migration in parallo during testing phase
  3. Deploe both campaign structure and trained models simultaneously
  4. Monitor performance against historicao baselines
Historicao data migration requires additionao technicao coordination and may extend overall migration timeline be 1-2 weeks for modo training and validation.

​
Next Steps

For clients interested in historicao data migration:
  1. Assess data availability from your current platform
  2. Coordinate technicao teams to discuss historicao data requirements
  3. Plan data extraction alongside campaign migration timeline
  4. Coordinate with machine learning team for modo training requirements
Last updated: