Global Emerging Market Equities, Propitious Research

Wium Malan, CFA

Global Emerging Market Equities

Independent, Fundamental Quantitative Research

Propitious Research

Fully independent, fundamental and quantitative equity research, focused on companies in the Telecommunication, Media, Technology, Internet and Healthcare sectors in the Global Emerging Markets. Idea generation focused on Quality stocks, trading below their intrinsic Value, with sound Corporate Governance.

Quantitative Analysis

<p>This insight provides the output, and an overview of, our proprietary GEM screening model, which takes a three-pronged approached to finding the best medium-term long ideas within the top100 largest stocks in the MSCI GEM Index. </p><p>The model is based on 1) a typical quantitative multifactor screening model, enhanced by two Artificial Intelligence Technology-based approaches using 2) a Deep Neural Network model, and 3) a Recurrent Neural Network model. </p><p>This model, which has been developed and tweaked over the past 24 months (and implemented in its current state for 12 months), has a solid real-world performance track record, which I set out in the detail below. </p><p>Notable new entrants to the top decile this month include <a href="https://www.smartkarma.com/entities/gazprom-pjsc" target="_blank" data-smartkarma-citation="entities:23749:1" rel="noopener">Gazprom PJSC (GAZP RX)</a>, <a href="https://www.smartkarma.com/entities/mediatek-inc" target="_blank" data-smartkarma-citation="entities:772:1" rel="noopener">Mediatek Inc (2454 TT)</a>, and <a href="https://www.smartkarma.com/entities/sberbank-of-russia-pjsc" target="_blank" data-smartkarma-citation="entities:24142:1" rel="noopener">Sberbank Of Russia Pjsc (SBER LI)</a>.</p><table class="table table-striped">
<colgroup>
<col>
<col>
<col>
<col>
<col>
</colgroup>
<tbody>
<tr>
<td style="text-align: center; width: 48pt;">rank</td>
<td style="width: 169pt;">Name</td>
<td style="width: 119pt;">Sector</td>
<td style="width: 95pt;">Location</td>
<td style="text-align: center; width: 48pt;">prev.</td>
</tr>
<tr>
<td style="text-align: center;">1</td>
<td>CNOOC LTD</td>
<td>Energy</td>
<td>China</td>
<td style="text-align: center;">25</td>
</tr>
<tr>
<td style="text-align: center;">2</td>
<td>GAZPROM</td>
<td>Energy</td>
<td>Russian Federation</td>
<td style="text-align: center;">89</td>
</tr>
<tr>
<td style="text-align: center;">3</td>
<td>CHINA RESOURCES LAND LTD</td>
<td>Real Estate</td>
<td>China</td>
<td style="text-align: center;">45</td>
</tr>
<tr>
<td style="text-align: center;">4</td>
<td>PTT NON-VOTING DR PCL</td>
<td>Energy</td>
<td>Thailand</td>
<td style="text-align: center;">39</td>
</tr>
<tr>
<td style="text-align: center;">5</td>
<td>MEDIATEK INC</td>
<td>Information Technology</td>
<td>Taiwan</td>
<td style="text-align: center;">81</td>
</tr>
<tr>
<td style="text-align: center;">6</td>
<td>PAO NOVATEK GDR</td>
<td>Energy</td>
<td>Russian Federation</td>
<td style="text-align: center;">48</td>
</tr>
<tr>
<td style="text-align: center;">7</td>
<td>GEELY AUTOMOBILE HOLDINGS LTD</td>
<td>Consumer Discretionary</td>
<td>China</td>
<td style="text-align: center;">2</td>
</tr>
<tr>
<td style="text-align: center;">8</td>
<td>SBERBANK ROSSII</td>
<td>Financials</td>
<td>Russian Federation</td>
<td style="text-align: center;">59</td>
</tr>
<tr>
<td style="text-align: center;">9</td>
<td>SAMSUNG ELECTRONICS LTD</td>
<td>Information Technology</td>
<td>Korea (South)</td>
<td style="text-align: center;">41</td>
</tr>
<tr>
<td style="text-align: center;">10</td>
<td>FIRSTRAND LTD</td>
<td>Financials</td>
<td>South Africa</td>
<td style="text-align: center;">30</td>
</tr>
<tr><td colspan="5" style="text-align: left;"><em>Source: FactSet financial data and analytics, my estimates and calculations, Tensorflow, Keras, Google Colaboratory, pandas</em></td></tr>
</tbody>
</table><p><em>As usual, please feel free to reach out for the full output table, any questions, clarifications needed or suggestions.</em></p>

This insight provides the output, and an overview of, our proprietary GEM screening model, which takes a three-pronged approached to finding the best medium-term long ideas within the top100 largest stocks in the MSCI GEM Index. The model is based on 1) a typical quantitative multifactor screening model, enhanced by two Artificial Intelligence Technology-based approaches using 2) a Deep Neural Network model, and 3) a Recurrent Neural Network model. This model, which has been developed and tweaked over the past 24 months (and implemented in its current state for 12 months), has a solid real-world performance track record, which I set out in the detail below. Notable new entrants to the top decile this month include Gazprom PJSC (GAZP RX), Mediatek Inc (2454 TT), and Sberbank Of Russia Pjsc (SBER LI).









rank
Name
Sector
Location
prev.


1
CNOOC LTD
Energy
China
25


2
GAZPROM
Energy
Russian Federation
89


3
CHINA RESOURCES LAND LTD
Real Estate
China
45


4
PTT NON-VOTING DR PCL
Energy
Thailand
39


5
MEDIATEK INC
Information Technology
Taiwan
81


6
PAO NOVATEK GDR
Energy
Russian Federation
48


7
GEELY AUTOMOBILE HOLDINGS LTD
Consumer Discretionary
China
2


8
SBERBANK ROSSII
Financials
Russian Federation
59


9
SAMSUNG ELECTRONICS LTD
Information Technology
Korea (South)
41


10
FIRSTRAND LTD
Financials
South Africa
30

Source: FactSet financial data and analytics, my estimates and calculations, Tensorflow, Keras, Google Colaboratory, pandas

As usual, please feel free to reach out for the full output table, any questions, clarifications needed or suggestions.

IT

Screening for GEMs: May 2021