Discover how to build a multi factor equity strategy in the SigTech platform.

Watch a step by step demo as SigTech Product Manager, Estèphe Corlin, demonstrates how to develop a strategy that uses the** **S&P500 index as the investment** **universe, employing Value, Quality and Momentum risk factors, as well as analysing and attributing the best performing portfolio vs the Fama French factors.

## Video transcript

In this video, we will be constructing a Multi Factor equity strategy in the SigTech platform.

The strategy will use the SP500 index as the eligible universe, rebalancing end of month, and employing Value, Quality and Momentum factors. We will test the performance of different combinations of our factors. And finally, analyse and attribute the best performing portfolio to the Fama french factors.

I will start by covering the platform fundamentals.

You can retrieve single stocks via the sig.obj.get method. Market prices can be retrieved through the history method. In this example, Apple's unadjusted last price is plotted. Equally, fundamental data, corporate actions, IBES analyst estimates and TRBC data can be accessed for single stocks.

The reinvestment strategy building block models the behaviour of single stock securities. It maintains long or short exposure to an underlying single stock, and adjusts for corporate actions and dividends in an event-driven way. You can call the history method on the reinvestment strategy, to return the total return for apple.

For our strategy, we define a custom end of month rebalance schedule and use the Equity Universe Filter to evaluate the SPX universe on each rebalance day. A reinvestment strategy is then built for every stock in your universe.

Here, the factors consist of Value, Quality and Momentum.

First, you need to define a factor exposure object, to which you can add different factors. Factors can be defined as fundamental or historic fields, as well as via custom methods.

Here we have defined four methods to compute the quality factors. Net debt-to-ebitda is used to evaluate financial leverage, the cash ratio is used to evaluate liquidity. Return on capital and EBIT margin are used to evaluate profitability. Price to book, price to free cash flow, price to equity and dividend yield are employed as value factors. Finally, we added a 6 month price return signal as a momentum factor.

You can now define a method to combine the various factors.

Factors can be combined by z_score sums under their respective factor types - Value, Quality and Momentum. Then you can apply factor weights to these summed values to calculate a final score. The top 20% of stocks ranked by this combined factor score are selected for our portfolio on each rebalance date.

SigTech's equity factor basket will construct and rebalance a single stock portfolio, given a universe and factor exposure object. An equally weighted allocation function is defined, to equally weight the holdings within our portfolio.

Different iterations of factor weights are backtested from 2021 onwards, and the resulting strategies are passed into SigTech's customisable performance report. You can see that the 50 - 50 value and quality strategy perform best, outperforming the index with a sharpe ratio just over 2 and annualised return of 30%. This strategy is retrieved and you can analyse its performance through the interactive performance plot.

Using SigTech, you can analyse your portfolio's risk profile through its exposure to the fama french factors. Start by loading the index returns of the three fama french factors - the market factor, the size factor - small minus big or SML, and the value factor - high minus low or HML.

Sigtech's factor exposure fit method conducts a multivariate regression of each stock’s returns within the portfolio to the three fama indices, and calculates an overall portfolio rolling exposure to the three factors over time.

For a more detailed view, a factor exposure report is generated on the portfolio's most recent weights. This report compares factor exposures, decompositions and distributions for our portfolio, versus an equally weighted universe.

Finally you can attribute the performance of your portfolio to the three fama factors by replicating the performance of each stock with weights in three factor indices, plus a residual value.

SigTech's tree plot allows you to see the top-down layers within your strategy. You can see that the replicated strategy has been modelled by weights in the fama french index, plus the residual term represented by the TTSI strategy.

The p&l breakdown method decomposes the performance of our replicated strategy at factor level. Returns are largely driven by the market factor until the reversal in January where value begins to perform.

SigTech enables multiple equities portfolio construction techniques. At this stage, you can define portfolio optimizations and constraints such as maximising exposure to certain factors, or minimising variance. Beta hedging can also be employed to turn our long only strategy market neutral.

Interested to learn more? Get in touch to schedule a personalised demo.

## Video transcript

In this video, we will be constructing a Multi Factor equity strategy in the SigTech platform.

The strategy will use the SP500 index as the eligible universe, rebalancing end of month, and employing Value, Quality and Momentum factors. We will test the performance of different combinations of our factors. And finally, analyse and attribute the best performing portfolio to the Fama french factors.

I will start by covering the platform fundamentals.

You can retrieve single stocks via the sig.obj.get method. Market prices can be retrieved through the history method. In this example, Apple's unadjusted last price is plotted. Equally, fundamental data, corporate actions, IBES analyst estimates and TRBC data can be accessed for single stocks.

The reinvestment strategy building block models the behaviour of single stock securities. It maintains long or short exposure to an underlying single stock, and adjusts for corporate actions and dividends in an event-driven way. You can call the history method on the reinvestment strategy, to return the total return for apple.

For our strategy, we define a custom end of month rebalance schedule and use the Equity Universe Filter to evaluate the SPX universe on each rebalance day. A reinvestment strategy is then built for every stock in your universe.

Here, the factors consist of Value, Quality and Momentum.

First, you need to define a factor exposure object, to which you can add different factors. Factors can be defined as fundamental or historic fields, as well as via custom methods.

Here we have defined four methods to compute the quality factors. Net debt-to-ebitda is used to evaluate financial leverage, the cash ratio is used to evaluate liquidity. Return on capital and EBIT margin are used to evaluate profitability. Price to book, price to free cash flow, price to equity and dividend yield are employed as value factors. Finally, we added a 6 month price return signal as a momentum factor.

You can now define a method to combine the various factors.

Factors can be combined by z_score sums under their respective factor types - Value, Quality and Momentum. Then you can apply factor weights to these summed values to calculate a final score. The top 20% of stocks ranked by this combined factor score are selected for our portfolio on each rebalance date.

SigTech's equity factor basket will construct and rebalance a single stock portfolio, given a universe and factor exposure object. An equally weighted allocation function is defined, to equally weight the holdings within our portfolio.

Different iterations of factor weights are backtested from 2021 onwards, and the resulting strategies are passed into SigTech's customisable performance report. You can see that the 50 - 50 value and quality strategy perform best, outperforming the index with a sharpe ratio just over 2 and annualised return of 30%. This strategy is retrieved and you can analyse its performance through the interactive performance plot.

Using SigTech, you can analyse your portfolio's risk profile through its exposure to the fama french factors. Start by loading the index returns of the three fama french factors - the market factor, the size factor - small minus big or SML, and the value factor - high minus low or HML.

Sigtech's factor exposure fit method conducts a multivariate regression of each stock’s returns within the portfolio to the three fama indices, and calculates an overall portfolio rolling exposure to the three factors over time.

For a more detailed view, a factor exposure report is generated on the portfolio's most recent weights. This report compares factor exposures, decompositions and distributions for our portfolio, versus an equally weighted universe.

Finally you can attribute the performance of your portfolio to the three fama factors by replicating the performance of each stock with weights in three factor indices, plus a residual value.

SigTech's tree plot allows you to see the top-down layers within your strategy. You can see that the replicated strategy has been modelled by weights in the fama french index, plus the residual term represented by the TTSI strategy.

The p&l breakdown method decomposes the performance of our replicated strategy at factor level. Returns are largely driven by the market factor until the reversal in January where value begins to perform.

SigTech enables multiple equities portfolio construction techniques. At this stage, you can define portfolio optimizations and constraints such as maximising exposure to certain factors, or minimising variance. Beta hedging can also be employed to turn our long only strategy market neutral.

Interested to learn more? Get in touch to schedule a personalised demo.

## Video transcript

In this video, we will be constructing a Multi Factor equity strategy in the SigTech platform.

The strategy will use the S&P500 index as the eligible universe, rebalancing end of month, and employing Value, Quality and Momentum factors. We will test the performance of different combinations of our factors. And finally, analyse and attribute the best performing portfolio to the Fama French factors.

I will start by covering the platform fundamentals.

You can retrieve single stocks via the sig.obj.get method. Market prices can be retrieved through the history method. In this example, Apple's unadjusted last price is plotted. Equally, fundamental data, corporate actions, IBES analyst estimates and TRBC data can be accessed for single stocks.

The reinvestment strategy building block models the behaviour of single stock securities. It maintains long or short exposure to an underlying single stock, and adjusts for corporate actions and dividends in an event-driven way. You can call the history method on the reinvestment strategy, to return the total return for apple.

For our strategy, we define a custom end of month rebalance schedule and use the Equity Universe Filter to evaluate the SPX universe on each rebalance day. A reinvestment strategy is then built for every stock in your universe.

Here, the factors consist of Value, Quality and Momentum.

First, you need to define a factor exposure object, to which you can add different factors. Factors can be defined as fundamental or historic fields, as well as via custom methods.

Here we have defined four methods to compute the quality factors. Net debt-to-ebit is used to evaluate financial leverage, the cash ratio is used to evaluate liquidity. Return on capital and EBIT margin are used to evaluate profitability. Price to book, price to free cash flow, price to earnings and dividend yield are employed as value factors. Finally, we added a 6 month price return signal as a momentum factor.

You can now define a method to combine the various factors.

Factors can be combined by z_score sums under their respective factor types - Value, Quality and Momentum. Then you can apply factor weights to these summed values to calculate a final score. The top 20% of stocks ranked by this combined factor score are selected for our portfolio on each rebalance date.

SigTech's equity factor basket will construct and rebalance a single stock portfolio, given a universe and factor exposure object. An equally weighted allocation function is defined, to equally weight the holdings within our portfolio.

Different iterations of factor weights are backtested from 2021 onwards, and the resulting strategies are passed into SigTech's customisable performance report. You can see that the 50 - 50 value and quality strategy perform best, outperforming the index with a sharpe ratio just over 2 and annualised return of 30%. This strategy is retrieved and you can analyse its performance through the interactive performance plot.

Using SigTech, you can analyse your portfolio's risk profile through its exposure to the Fama French factors. Start by loading the index returns of the three Fama French factors - the market factor, the size factor - small minus big or SML, and the value factor - high minus low or HML.

Sigtech's factor exposure fit method conducts a multivariate regression of each stock’s returns within the portfolio to the three Fama indices, and calculates an overall portfolio rolling exposure to the three factors over time.

For a more detailed view, a factor exposure report is generated on the portfolio's most recent weights. This report compares factor exposures, decompositions and distributions for our portfolio, versus an equally weighted universe.

Finally you can attribute the performance of your portfolio to the three fama factors by replicating the performance of each stock with weights in three factor indices, plus a residual value.

SigTech's tree plot allows you to see the top-down layers within your strategy. You can see that the replicated strategy has been modelled by weights in the Fama French index, plus the residual term represented by the TTSI strategy.

The p&l breakdown method decomposes the performance of our replicated strategy at factor level. Returns are largely driven by the market factor until the reversal in January where value begins to perform.

SigTech enables multiple equities portfolio construction techniques. At this stage, you can define portfolio optimizations and constraints such as maximising exposure to certain factors, or minimising variance. Beta hedging can also be employed to turn our long only strategy market neutral.

Interested to learn more? Get in touch to schedule a personalised demo.

Share:

## Disclaimer

*This document is not, and should not be construed as financial advice or an invitation to purchase financial products. It is provided for information purposes only and is subject to the terms and conditions of our disclaimer which can be accessed at: https://www.sigtech.com/legal/general-disclaimer*