PMS Bazaar recently organized a webinar titled “Estee's Approach to Generating Long term Alpha,” which featured Mr. Parul Joy Saini, Vice President, Strategy (Designated Additional Person for PMS and Fund Manager – Long Alpha), Estee Advisors Private Limited. This blog covers the important points shared in this insightful webinar.

The webinar blog features insights from Mr. Parul Joy Saini on the quantitative investment philosophy behind the LongAlpha strategy. It explores how factor investing, data-driven portfolio construction, dynamic risk management, and robust technology work together to deliver consistent long-term performance. The blog also highlights the evolution of quantitative investing in India and the growing role of artificial intelligence in investment research.

Key aspects covered in this webinar blog are

• The core building blocks of factor investing 
• Dual-block model and portfolio construction 
• Historical performance and risk discipline 
• Robust operational infrastructure and data integrity 
• Managing portfolio turnover and scalability 
• Dynamic adaptation to market regimes 
• Evolution of quantitative investing in India 
• Portfolio allocation and risk framework 

Summary: Mr. Parul Joy Saini explained that the LongAlpha strategy is a factor-based quantitative investment model  that evaluates stocks using over 80 metrics across quality, momentum, volatility, leverage, and value. A dual-layer ranking process ensures balanced sector exposure while constructing a diversified portfolio of 100–120 BSE 500 stocks, rebalanced monthly. The strategy aims to outperform the S&P BSE 500 Total Return Index by around 5% over the long term through disciplined, data-driven investing. Robust automation, high-quality historical data, and continuous factor monitoring support scalability, cost efficiency, and risk management. The model dynamically adapts to changing market conditions while maintaining consistent investment discipline.

The Core Building Blocks of Factor Investing

Mr. Parul Joy Saini started by explaining that the foundation of the LongAlpha strategy relies entirely on factor-based quantitative investing. Rather than depending on traditional discretionary stock picking driven by daily news, the model evaluates companies using over eighty distinct quantitative metrics categorized into five broad buckets.

The first bucket focuses on quality factors, identifying robust businesses with stable and high returns on assets and equity. The second bucket evaluates momentum, capturing stocks that have demonstrated strong upward price trajectories over the preceding year—a factor historically proving highly effective within Indian markets. The third category incorporates volatility measures, analyzing stock betas and standalone volatility to harness low-volatility outperformance anomalies. The fourth bucket assesses leverage, tracking debt-to-equity and debt-to-EBITDA ratios to screen out overly cyclical or highly indebted enterprises. Finally, the value bucket examines metrics such as price-to-earnings and price-to-book ratios. By synthesizing these diverse inputs, the framework constructs a comprehensive multi-factor matrix.

Dual-Block Model and Portfolio Construction

The architecture of the LongAlpha model operates through a structured two-block process to ensure balanced market exposure. Mr. Parul Joy Saini noted that the first block ranks the entire S&P BSE 500 universe across all eighty-plus factors simultaneously. However, because certain sectors naturally exhibit unique financial traits - such as higher baseline leverage within the financial services sector - a secondary block evaluates stock rankings strictly within individual sectors.

This sectoral screening prevents the model from inadvertently discarding entire industries or taking extreme overweights. Following this dual-layer ranking, the system evaluates trailing performance trends and inter-factor correlations. This continuous optimization leads to a well-diversified final portfolio comprising roughly 100 to 120 cash equities from the BSE 500 index. Portfolio rebalancing occurs predominantly on a monthly basis, positioning the strategy as a low-frequency quantitative model compared to high-frequency trading platforms.

Historical Performance and Risk Discipline

When evaluating performance targets, Mr. Parul Joy Saini highlighted that the LongAlpha strategy aims to generate an excess return of approximately five percent over the S&P BSE 500 total return index over the long term, net of fees and expenses. Since its inception, the product has closely tracked this objective, delivering robust alpha despite periodic market headwinds.

While absolute and relative drawdowns are anticipated in long-only equity strategies—notably during challenging market environments in recent years - these fluctuations remain well within pre-defined statistical confidence bands. This empirical consistency reinforces the team's confidence that the core quantitative model operates effectively through varying market cycles without requiring emotional intervention.

Robust Operational Infrastructure and Data Integrity

A crucial element emphasized during the discussion was the technological and operational infrastructure supporting the LongAlpha portfolio management service. Mr. Parul Joy Saini pointed out that the strategy benefits from fully automated account onboarding, daily position reconciliations with custodians, and automated post-trade allocations. Furthermore, the system accommodates customized client requirements, such as managing specific banlists to automatically exclude designated stocks like employee-restricted entities.

Underpinning this entire execution framework is a massive investment in point-in-time data infrastructure. Because companies frequently restate earnings and undergo corporate actions, maintaining historical data integrity is essential. By ensuring that back-testing models utilize precise historical metrics without look-ahead bias, SD Advises maintains the highest standards of quantitative accuracy and regulatory compliance.

Managing Portfolio Turnover and Scalability

Addressing common apprehensions regarding the high turnover typically associated with quantitative models, Mr. Parul Joy Saini explained the specific mechanisms implemented to maintain cost-efficiency and operational discipline. The strategy avoids daily rebalancing, opting instead for monthly or semi-annual intervals designed to capture multi-month market trends rather than reacting to fleeting daily price fluctuations. Furthermore, utilizing an established library of over eighty stable quantitative factors prevents erratic ranking shifts, ensuring greater stability across the portfolio.

The resulting output comprises a well-diversified portfolio of more than one hundred stocks, which significantly reduces market impact costs and execution slippage compared to concentrated investment books. Mr. Parul Joy Saini emphasized that every back-test meticulously evaluates performance on a post-transaction cost basis, incorporating estimated market impact relative to portfolio size. This ensures that scaling up capital does not distort execution efficiency. Consequently, the firm is fully prepared to scale its assets under management significantly from current levels without suffering any performance degradation.

Dynamic Adaptation to Market Regimes

The LongAlpha model operates as a dynamic factor model rather than a rigid, static framework. Mr. Parul Joy Saini detailed that the system continuously monitors multi-month shifts in factor performance, volatility, and inter-factor correlations to adapt portfolio exposures organically. Rather than reacting to short-term market noise or attempting to time the market through explicit cash calls during volatile periods, the strategy remains consistently invested across all market cycles.

Highlighting real-world resilience during geopolitical tensions in West Asia and sudden market corrections, Mr. Parul Joy Saini noted that the model successfully participated in market downswings with reduced downside capture, while strongly outperforming during subsequent rebounds. When temporary relative drawdowns occurred in challenging years such as 2022 and 2025, the performance remained comfortably within pre-calculated statistical confidence bands, confirming that the underlying model remained fully intact. Additionally, the investment team integrated enhanced value and quality factors following the 2022 review to further fortify the strategy.

Evolution of Quantitative Investing in India

Discussing the broader landscape of quantitative finance in India, Mr. Parul Joy Saini observed that while traditional discretionary investing still holds a dominant market share, systematic investing is gradually gaining strong traction as market participants mature. Early quantitative strategies relied strictly on static factor weights, but modern approaches have evolved into dynamic, adaptive frameworks. While human-driven discretionary managers often aim for sharp short-term gains whose long-term sustainability is difficult to measure, quantitative models offer disciplined, consistent, and repeatable outcomes over extended horizons.

Looking toward the future, Mr. Parul Joy Saini highlighted that the team utilizes artificial intelligence and machine learning tools to accelerate internal research and coding processes. While the core strategy currently builds upon validated financial hypotheses rather than letting AI make fully autonomous trading decisions, future evolutions may incorporate alternative data sources such as earnings call sentiment analysis and pure data-driven machine learning algorithms.

Portfolio Allocation and Risk Framework

When examining portfolio construction and risk parameters, Mr. Parul Joy Saini clarified that the strategy maintains high active share, naturally resulting in a balanced representation across large, mid, and small-cap segments depending on prevailing factor rankings. The dual-block construction process ensures adequate sectoral representation - preventing extreme concentration while allowing natural underweights in sectors like financials due to strict leverage and quality scorecards.

Risk management within the PMS structure relies heavily on monitoring absolute and relative drawdowns against established confidence intervals, alongside rigorous daily position reconciliations with custodians. While current regulations limit derivative hedging within long-only PMS products, the firm possesses extensive domestic and international long-short experience, positioning them well to adapt as regulatory frameworks evolve to permit broader derivative and unlisted asset exposures.

Mr. Parul Joy Saini covered all the topics mentioned above in-depth and answered questions from the audience toward the end of the session. For more such insights on this webinar, watch the recording of this insightful session through the appended link below.