Worldwide ASSET ALLOCATION AND STOCK SELECTION .


67 views
Uploaded on:
Category: Product / Service
Description
Worldwide Resource Distribution AND STOCK Choice. Task # 1 Little Top LONG-SHORT System FIRST-YEAR Conquers Daniel Grundman, Kader Hidra, Damian Olesnycky, Jason Trujillo, Alex Volzhin. Philosophy. Objective: to recognize long-short system for exchanging US little top stocks utilizing Reality Set.
Transcripts
Slide 1

Worldwide ASSET ALLOCATION AND STOCK SELECTION ASSIGNMENT # 1 SMALL CAP LONG-SHORT STRATEGY FIRST-YEAR BRAVES Daniel Grundman, Kader Hidra, Damian Olesnycky, Jason Trujillo, Alex Volzhin

Slide 2

Methodology Goal: to recognize long-short system for exchanging US little top stocks utilizing Fact Set. Universe Definition: US stocks with market top from $300M to $2B. System: Buy first quintile, Short fifth quintile. Benchmark: S&P 500 In-test period: Jan, 1995 – Dec, 2004 Out-of-test period: Jan-Dec, 2005

Slide 3

Factors We tried many variables yet settled on three: One-month return Six-month return Current cost to 52-week high Additionally, we attempted different mixes of these components (two-element and tree-figure models)

Slide 4

Strategy Based on 1-Month Return 1-Month Return 1-Month Alpha

Slide 5

Strategy Based on 6-Month Return 6-Month Return 6-Month Alpha

Slide 6

Current Price to 52-Week High Price to 52-Week High Alpha Price to 52-Week High Return

Slide 7

Other Explored Factors notwithstanding the past 3 elements, we attempted a few different measurements: Book to Market Price to Earnings Dividend Yield Return on Equity Revision Ratio However, we observed every one of them to be of little esteem.

Slide 8

Book to Market Price Book to Price Return Book to Price Alpha

Slide 9

Price to Earnings P/E Return P/E Alpha

Slide 10

Revision Ratio Revision Ratio Return Revision Ratio Alpha

Slide 11

Returns Our one-calculate models conveyed great returns: 1-Month Returns Model +6.98% 6-Month Returns Model +4.26% Price to 52-Week High +3.55% However, two-consider models were shockingly better: 1-Month Return & Price to 52-Week High +6.95% 6-Month Return & Price to 52-Week High +4.55%

Slide 12

Bivariate Model: 1-Month Return & Price to 52-Week High

Slide 13

Beta for Bivarate P to 52High & 1 Month Return Model

Slide 14

Bivariate Model: 6-Month Return & Price to 52-Week High

Slide 15

Multivariate Model Multivariate Model Return Multivariate Model Alpha

Slide 16

Scoring We utilized scoring for bi-variate display (1-month return and cost to 52-week high) For 1-month return: first quintile +5, fifth quintile - 5 Price to 52-week high: first quintile +3, fifth quintile - 3 More weight on 1-month return since single-element model in view of 1-month return is better than that in light of cost to 52-week high.

Slide 17

In-Sample Two-Factor Model: 1-Month Return & Price to 52-Week High with Scoring In-Sample Model w/Scoring Return In-Sample Model w/Scoring Alpha

Slide 18

Beta for Bivarate 52-P and 1-Month Return Scoring Model

Slide 19

Out-of-Sample Testing We utilized the period from January, 2005 to December, 2005 for the out-of-test testing of our best model (two-calculate: 1-month return & current cost to 52-week high). Annualized Returns - Benchmark Return: 0.4% Our model without scoring: 11.79% Our model with scoring: 12.07%

Slide 20

Out-of-Sample Two-Factor Model: 1-Month Return & Price to 52-Week High w/o Scoring Out-of-Sample Model Return Out-of-Sample Model Alpha

Slide 21

Out-of-Sample Two-Factor Model Beta: 1-Month Return & Price to 52-Week High without Scoring

Slide 22

Out-of-Sample Two-Factor Model: 1-Month Return & Price to 52-Week High with Scoring Out-of-Sample Model w/Scoring Alpha Out-of-Sample Model w/Scoring Return

Slide 23

Out-of-Sample Two-Factor Scoring Model Beta: 1-Month Return & P to 52-W High with

Slide 24

In-Sample Results (1/2) Heat Map In-Sample WITHOUT Scoring: Quintile 1 has NOT the most elevated normal return. Just 3/10 years have the most noteworthy returns. Here we are worried by 2003 when we really got the least returns in Quintile 1. The spread would have squashed us! Quintile 5 has the least normal return. 5/10 years have the most minimal returns. Here we are worried by 2003 when we really got the most elevated returns in Quintile 5.

Slide 25

In-Sample Results (2/2) Heat Map In-Sample WITH Scoring: The scoring screen reduces our worries: Fractile 1 has the most astounding normal return. 8/10 years have the most astounding returns. The scoring disposes of the 2003 pulverize! Fractile 5 has the most reduced normal return. 10/10 years have the most reduced returns.

Slide 26

Out-of-Sample Results (1/2) Heat Map Out of Sample WITHOUT Scoring: Quintile 1 has the most noteworthy normal return. Just 3/12 months have the most noteworthy returns. Here we are worried by these 2 months where we really got the most reduced returns in quintile 1. Quintile 5 has the least normal return. 8/12 months have the most reduced returns. Here we are worried by these 2 months where we really got the most elevated returns in quintile 5. The Long/Short spread is tasteful: 36%

Slide 27

Out-of-Sample Results (2/2) Heat Map Out of Sample WITH Scoring: The scoring screen reduces our worries: Quintile 1 has the most noteworthy normal return and beat the unscored screen by a long shot! Quintile 1 has the most noteworthy normal return. 10/12 months have the most elevated returns. Quintile 5 has the most reduced normal return and failed to meet expectations the unscored screen by a wide margin! Quintile 5 has the least normal return. 9/12 months have the least returns. The Long/Short spread is tasteful: 147%.

Slide 28

Long/Short Distributions Positively Skewed After Scoring

Slide 29

Concerns Transaction Costs Short Selling Constraints Execution Volatility/Exit Signals Fact Set

Slide 30

Concerns Transaction Costs Monthly rebalancing Many months have >50% change in fractile parts. Expansive number of securities ~60 Stocks per fractile every month

Slide 31

Concerns Short Selling Constraints Dealing just with little top securities. May be constrained chance to short offer some securities.

Slide 32

Concerns Execution How to execute as a genuine exchanging system. At the point when to run demonstrate? At the point when do you make exchanges?

Slide 33

Concerns Volatility and Exit Signals Portfolios are not Beta nonpartisan and general betas are for the most part over 1. No parameters set for selling portfolios. In test we had a few terrible months. Given the high unpredictability of little tops, there is the potential for extensive misfortunes.

Slide 34

Concerns Fact Set Limited information of the instrument. Comes about appear to be too great. By and by we would run tests to confirm that what we accept is going on is really happening.

Slide 35

Limitations Primary restriction is the reserve estimate for which this is perfect. Generally couple of securities Low market capitalizations Solution: Change screen Wider market top range Low exchanging volume necessity

Slide 36

Summary We discover the aftereffects of our investigation to be extremely convincing. The enormous test is effective and appropriate execution. Appropriate investigation of exchange expenses is required. We would likewise prescribe a further audit of the information before pushing ahead.

Recommended
View more...