This template is brought to you by Optimizely, a leading experimentation platform.
Experiment plan and results | Replicating Results of Transformer Fusion Model using Favourita Dataset |
---|---|
Experiment owner | |
Reviewers | |
Approver | |
Optimizely link | |
Jira ticket(s) | |
Status | IN REVIEW / IN PROGRESS / COMPLETE |
On this page |
Stakeholder summary
📋 Experiment planning
Overview: Replicating Results of Transformer Fusion Model using Favourita Dataset
https://arxiv.org/pdf/1912.09363.pdf
Current Roadblock:
|
Hypothesis
We hypothesize that DA-RNN with Transfer learning/ Transformer model with Transfer Learning
will decrease MSE/RMSE
because of the incorporation of embeddings
Metrics
MSE
RMSE
Targeting
Where will this experiment run?
Who will see it?
What is the traffic allocation (% in total let in based on targeting)?
Variations
A: Control | B: Variation | C: Variation | |
---|---|---|---|
Screenshot | |||
% of visitors/users to see each variation |
Pre-analysis
Add any baseline data or pre-analysis you have for this experiment. Add planned sample size and time to run.
Notes
📊 Results
Experiment start | |
---|---|
Experiment end |
|
Link to results in Optimizely | |
Conclusion | INCONCLUSIVE / HYPOTHESIS PROVED |
Add a short summary of the metrics below and whether you hit significance.
A: Control | B: Variation |
| A: Control | C: Variation |
| |
---|---|---|---|---|---|---|
Cohort size | ||||||
Primary metric |
|
| ||||
Other metrics |
✨ Conclusions
Highlights
Primary goal