Downloaded 18 times
Uploaded byLooker
Improving Data Modeling Workflow
LendingHome is an advanced mortgage marketplace platform that connects investors to safe, high-yield loans and streamlines the borrowing process with rapid prequalification and funding. The document discusses the integration of Looker as a data exploration solution to improve data modeling workflows and analytics, allowing data scientists to efficiently prepare data and evaluate models. The emphasis is on enhancing operational processes through rigorous analytics and ensuring quality in reporting and decision-making.
More Related Content
Similar to Improving Data Modeling Workflow
![[Redis Released]- FalkorDB - Redis + Graph Agentic Memory’s Secret Sauce](https://cdn.slidesharecdn.com/ss_thumbnails/redisreleased-falkordbslidedeck-1125-251115194922-e1c0046b-thumbnail.jpg?width=640&height=640&fit=bounds)
Improving Data Modeling Workflow
- 1. Improving the Data ModelingWorkflow October 28, 2014
- 2. LendingHome is themost advanced mortgage marketplace platform in the world What Is LendingHome?
- 3. What is LendingHome? Simple,efficient borrower experience Investors are matched to safe, high-yield loans World-class mortgage ops process driven by transparent analytics Statistical models for credit, underwriting, pricing, sales, marketing
- 4. LendingHome: Mortgage Marketplace •Fastest loan funded in 72 hours • Borrowers prequalify in 3 minutes Investors are matched to safe, high-yield loans • Line-item accounting for payout tracking • Proceeds from loans wired in under a second
- 5. Looker is adata exploration solution that operates in the database to enable organizations to explore data in all its detail. What Is Looker?
- 6. Some of Looker’sCustomers
- 7. LendingHome: Operations World-class operationalprocess driven by transparent analytics • Integrations with over 20 vendors • Rigorous 96-item checklist • Looker-driven workflow measures quality and timing of entire process • Highly complex reporting, dashboards are easy in Looker
- 8.
- 9.
- 10. The Challenge Data scientistscreate value by creating actionable models More time spend preparing data and evaluating results than using heavy data science techniques How to speed up analytical cycles
- 11. Focusing on Expertise Define Goals DataCleaning and Shaping Model Dev Expertise “Work” Model Eval
- 12. Our Example 38 millionflights between 2000 and 2005 Carrier information, departure and arrival location, manifest data, aircraft data Modeling on-time rates
- 13. Getting Started Analytics asthe shortcut to variable selection
- 14. Data Cleaning Analytics canprovide a distinct advantage in the constant struggle for clean data
- 15.
- 16.
- 17. Pulling Data Analytics allowdata scientists to lever analytical modeling to easily grab reshaped data - Time-zone functions - Sub-select functions - Cleaned/filtered data
- 18. LendingHome: Quant Modeling • Creditmodels learned over 25M loans, 4B payments, macroeconomic factors • Scoring transparent to borrowers, investors • Finds and predict borrower conversion from 180M RE transactions • Feature extraction, data exploration, train/test splits, model analysis in Looker
- 19.
- 20.
- 21. Building The DataModel Let’s try a simple model:
- 22.
- 23. Continuing Our Example Re-usingthat same analytics process, we can explore our data more seamlessly
- 24.
- 25.
- 26.
- 27.
- 28.
- 29. Try Looker onyour own data. Looker.com/trial
- 30.
Editor's Notes
- #9 Blank = nothing to do Query over those 96 checklist items, 20+ vendors View into many standard 800+ page closing packages distilled to one dashboard Final query > 1300 lines of sql
- #10 ~100 of 1300 lines Tedious SQL case encapsulated… Nested inside counts Encapsulated subselects -> Not doable by hand
- #14 Slicing up data to examine trends.
- #15 Midnight flights cannot really be this bad, and why are there so many
- #16 The same cleaning applies to problems like dates, missing data, grouping data – modeling in database helps!
- #17 Correlated/co-dependent variable selection (day of week + time of day) can be especially difficult. Quick analytical exploration can reveal whether these variables need to be included.
- #20 FICO is mostly normal… for default modeling, unclear what to use. - proportion within bucket? - mixture model? - what about function of loss? Of principal? Are those correlated? Easy to split by state, hpi within time window, loan type in looker (no script, no query editing, just click) Easy to overlay model scores, compare models vis a vis factors
- #21 Noisy features are easy to see. No way DTI is < 10% for approx half of borrowers.
- #27 Drillable, iterative confusion matrix … in a few clicks Explore factors’ impact by adding variables (can’t show this) -> biz/finance users can peek into the model this way Filter on version -> one algorithm/dataset pair Easily visualize default rate vs return rate, stratify by loan size, pre/post crisis, etc, etc
- #28 We just got access to database of plane types, now rather than porting everything into our modeling software, we can run analytics again to examine whether the data (like plane size), appears to have significant bias in our forecasts. Since we didn’t have this data at model-time, quick analytical views can be an effective way to quickly evaluate whether there is pickup to be had re-modeling. In closing – simple tools when you can, analytics are simple