Real Estate Portfolio Optimization Midpoint Presentation Friday October 26, 2018 Iowa State University Senior Design ARIN: Analytics Research Intelligence Network analytics@scale Classification: Company Confidential
Meet the Team Blake Kevin Nickolas Roberts Johnson Moeller Project Lead / Test Engineer / Report Manager / Backend Frontend Backend Software Computer Software Engineering Engineering Engineering Leelabari Colton Goode Fulbel Meeting Scribe / Backend Meeting Facilitator / Frontend Computer Engineering, Management of Software Engineering Information Systems 2 Classification: Company Confidential Classification: Company Confidential
BLUF Bottom Line Up Front Our mission is to design and develop a portfolio optimization system that meets the unique needs of a commercial real estate portfolio manager. Project Scope 1 2 3 Gather requirements. Master the real estate Design the system and Test, iterate, and report out. domain and portfolio create a working prototype. optimization. 3 Classification: Company Confidential
Intro to Portfolio Optimization The Problem and Plan Agenda Preliminary Results Next Steps 4 Classification: Company Confidential Classification: Company Confidential
Intro to Portfolio Optimization The Problem and Plan Agenda Preliminary Results Next Steps 5 Classification: Company Confidential Classification: Company Confidential
Calculate Inputs Local Knowledge Portfolio optimization requires Allow the user to express their estimates of expected return and beliefs about a given asset, the asset covariance matrix market, lifecycle, or property type 2 1 Portfolio Optimization Algorithm searches for the The user defines portfolio 3 Compare thousands of runs to 4 constraints. mixture of assets that minimizes identify the best strategies the objective function (e.g. e.g. The portfolio’s allocation to risk-adjusted return) NYC must be 35-40% Optimize Define Constraints 6 Classification: Company Confidential
Intro to Portfolio Optimization The Problem and Plan Agenda Preliminary Results Next Steps 7 Classification: Company Confidential
The Problem Facing Principal Lacking an Internal Market Level Data Analysis is Portfolio Optimization Tool Outsourced No portfolio optimization currently being Costar - expensive, lengthy reports done in house Costar Lacks: Lacking capabilities: - customization/configuration of - representing data in graphs analysis - automatically optimizing with - the ability to extend the report into constraints more niche analysis - repeating this analysis swiftly - cannot have access to confidential fund data 8 Classification: Company Confidential
The Solution A software that enables PM’s to perform their own portfolio optimizations Efficient, Reliable Cost Effective Flexible, Extendable Distributed software Use your data to get your Reduces reliance on available from any results the way you want Costar computer them Optimizations can be done Easy to run similar The software is open for internally, by any PM at optimizations at future suggestions by its users! their leisure times 9 Classification: Company Confidential
Intro to Portfolio Optimization The Problem and Plan Agenda Preliminary Results Next Steps 10 Classification: Company Confidential
Preliminary Results Frontend Design Markowitz in Python Python Flask Server Investigation Utilizes NCREIF data User interface mockups Flask server boilerplate were created Optimization is done per Two endpoints configured: market Frontend framework - optimization form - Dash - optimized weights response Configurable property type and timeframe 11 Classification: Company Confidential
represents a Screen flowchart represents transition viewable page from one page to another View unoptimized View optimized Options page Home Page data page data page ● import a ● Update expected ● show current ● show optimized portfolio returns portfolio portfolio holdings ● optional custom holdings by by geography, constraints geography, region, etc. in ● import new region, etc. in pie/bar graphs expected returns pie/bar graphs ● give recommended ● summarize actions as to what expected risk to buy and sell and return based on return and risk User presses the Can also view efficient frontier User will click the User can view data optimize button to graph with comparison to import button to and then move on to send the data to current portfolio and export upload portfolio the options page the backend results via email data via a csv file 12 Classification: Company Confidential
Start your Optimization Experience Right 13 Classification: Company Confidential
Analyze your Portfolio on Various parameters 14 Classification: Company Confidential
Define your Portfolio’s Custom Constraints 15 Classification: Company Confidential
Intro to Portfolio Optimization The Problem and Plan Agenda Preliminary Results Next Steps 16 Classification: Company Confidential
Project Timeline Midpoint Minimal Viable Iteration and Final Product Presentation Product Refactor December 2018 March 2019 April 2019 Today March 2019 May 2019 Final Prototype User Testing Presentation 17 Classification: Company Confidential
Thank You – Questions? Classification: Company Confidential Classification: Company Confidential
Classification: Company Confidential Classification: Company Confidential
END OF PRESENTATION Following slides hold information/notes that may or maynot be added to the presentation. Classification: Company Confidential Classification: Company Confidential
Round 1 Feedback (Ben) • It would be great to cover the requirements you have discovered so far. Shows the audience that you are creating a solution fit for their needs and paints the picture of what they could do with it. • Can you briefly touch on the basics and benefits of portfolio optimization in the intro? What are the risks or downsides of not using portfolio optimization? This helps remind the audience of the immense value your tool could create. You could consider using the slide on the next page. • I am proposing a small change for the first few slides. 1) Title slide 2) Team intro 3) Bottom Line Up Front – 10 seconds to highlight why they should care about the next 20 slides 4) Agenda – Remove team intro as a section. Add a new section or go to 3. Either is ok. • Be consistent with the location and size of the title of each slide. Aim for “Action Titles”. e.g. “Define your portfolio’s custom constraints” is better than “UI Mockup – Options Panel” 21 Classification: Company Confidential
Project Objectives 1. Literature review of portfolio optimization 2. Gather requirements from researchers and portfolio managers including use cases, constraints, & best practices 3. Prototype constrained optimization models in R or Python 4. Propose a design for a user interface that can initialize optimization models and portfolio simulations. Design visualizations and summary statistics for the current portfolio, optimal portfolios, and simulation results 5. Prototype the proposed system using open source libraries 6. Test prototype on a sample dataset from existing fund and review for accuracy 7. Present buy/sell recommendations to the portfolio managers with a description of how the action will impact the portfolio 22 Classification: Company Confidential
Project Deliverables 1. Working prototype of user interface using sample fund data 2. Well documented code and data sources needed to reproduce results and handoff to process owners 3. Detailed report describing project background, methodology, results, and next steps. 4. Documentation describing the current system and a proposal for maintenance and improvements 5. Midpoint and final presentations to Principal stakeholders 6. Project poster providing a visual snapshot of written report 23 Classification: Company Confidential
24 Classification: Company Confidential
Calculate Inputs Local Knowledge Portfolio optimization requires Allow the user to express their estimates of expected return and beliefs about a given asset, the asset covariance matrix market, lifecycle, or property type 2 1 Portfolio Optimization Algorithm searches for the The user defines portfolio 3 Compare thousands of runs to 4 constraints. mixture of assets that minimizes identify the best strategies the objective function (e.g. e.g. The portfolio’s allocation to risk-adjusted return) NYC must be 35-40% Optimize Define Constraints 25 Classification: Company Confidential
Recommend
More recommend
