Unlocking daily intelligence and holdings from 2,000+ institutional mutual funds and ETFs representing $4 trillion in industry assets - unlike ever before.
NextFolio’s Ensemble Active is a first-of-its-kind investment approach that integrates high-conviction positions from multiple active managers, leveraging real-time insights and unique machine learning technology coupled with expert manager selection to create adaptive actively managed portfolios.
Ensemble Methods, a branch of machine learning used to enhance forecast accuracy in solving complex challenges, have over 250,000 published applications today.
By treating mutual funds as models and stock holdings as forecasts, real-time replication technology unlocks the power of Ensemble Methods in active management for the first time—redefining portfolio construction with a data-driven, systematic approach.
Ensemble Methods combine the strengths of multiple managers, leveraging diverse perspectives to reduce bias, enhance predictive accuracy, and improve risk-adjusted returns over time.
Ensemble Alpha™is the excess return potential from using ensemble methods to identify and invest in only high-conviction stocks.
This is measured by comparing the return generated by a NextFolio ensemble active portfolios with the underlying basket of funds from which high- conviction stocks are drawn. In this manner, Ensemble Alpha™ seeks to capture collective skill while avoiding dilutive overdiversification.
NextFolio Ensemble Active strategies deliver diversified, real-time portfolios by drawing from the collective high-conviction stock picks of select mutual fund and ETF managers. NextFolio Ensemble Active strategies are easy for investment firms to implement, providing a unique, scalable, differentiated approach to traditional active management.
Analyze hundreds of funds and thousands of stocks using proprietary quantitative models and qualitative insights to construct a curated selection of competitively advantaged institutional-quality funds.
The fund replication system leverages machine learning to replicate the daily holdings of selected mutual funds and ETFs in real-time.
Combining machine learning technology to identify high-conviction stocks across multiple managers with ensemble methods and NextFolio's portfolio construction guidance, NextFolio's Ensemble Active portfolios are developed to optimize real-time insight with state-of-the-art data science to focus on Ensemble Alpha™.
Quarterly evaluations and real-time monitoring ensure selected funds maintain performance and strategic consistency.
Help your firm and clients thrive with real-time, high-conviction stock picks from leading fund managers.
Find answers to common questions about NextFolio and Ensemble Active.
NextFolio aims to redefine active management by offering data-driven strategies that overcome the limitations of traditional single-manager approaches.
Our founders, with over 60 years of combined wealth management experience, spent nearly five years evaluating the Ensemble Active approach and recognized its breakthrough potential. In 2024, they launched NextFolio to deliver institutional-grade Ensemble Active Portfolios to banks, RIAs, broker-dealers, institutions, and family offices.
NextFolio offers ready-to-implement strategies designed for banks, RIAs, broker-dealers, institutions, and family offices, helping them drive asset growth through differentiation and scale that no other firms can provide.
NextFolio addresses the challenge of traditional active management in four ways:
Data science is at the core of how NextFolio develops its strategies, accessing machine learning to analyze real-time holdings and build strategies based on high-conviction stock picks of multiple mutual fund managers. Machine learning powers Ensemble Active’s ability to access and analyze the real-time holdings and weights of mutual funds (information typically not publicly available), offering unmatched visibility into high-conviction stock picks.
The primary source of holdings data comes from form N-Port filings, which registered investment companies (RICs) are required to file quarterly with a 60-day lag (and just for the last reported month of the fund’s fiscal quarter). Those quarterly holdings are “converted” to daily holdings through machine learning techniques applied by NextFolio’s technology partner. NextFolio’s technology partner creates daily replication portfolios of mutual fund holdings using machine learning that has been able to produce over a 99% correlation with daily fund NAV changes. Through this replication technology, NextFolio accesses a “best estimate” of how a fund’s holdings evolve over time. For ETFs, which report their holdings daily, no replication is required; data can be accessed directly.
Ensemble methods (or learning) involve multiple models, often referred to as base models or weak learners, combining their predictions to harness the power of collective knowledge and multiple viewpoints.
Ensemble Active is the process by which NextFolio tracks the daily holdings of mutual fund/ETF managers across the U.S., using this data to construct portfolios that reflect real-time, high-conviction stock selection from a curated set of 10-15 competitively-advantaged institutional-quality managers.
NextFolio addresses the challenge of traditional active management in four ways:
Ensemble Alpha™ represents the excess returns achieved through using ensemble methods to identify and invest in only high-conviction stocks. This is measured by comparing the return generated by a NextFolio Ensemble Active Portfolio with the underlying basket of funds from which high-conviction stocks are drawn.
In this manner, Ensemble Alpha™ seeks to capture collective skill while avoiding dilutive overdiversification.No. Ensemble Active Portfolios are composed solely of long-only, U.S. domestic equity securities, drawn directly from corresponding benchmarks. This ensures that all portfolios are style-pure, meaning a Large Core portfolio, for example, contains only stocks from the Russell 1000 benchmark.
Fund of Funds combine entire funds without considering overlap in stock selection. This compounds the overdiversification drawbacks already present in single funds that dilute alpha. Ensemble Active Portfolios only use high-conviction ideas sourced across multiple funds, determining which of those stocks to own directly.
Fund of Funds rely on entering into sub-advisory agreements with fund managers and paying them fees for their service. Ensemble Active Portfolios use only publicly available information to inform their stock selection process, providing greater flexibility in hiring and firing decisions.
Yes, while fund selection and portfolio construction overlap conceptually, they are distinct processes.
Ensemble Active Portfolios require a curated set of competitively advantaged managers. It’s not just about picking strong funds; it’s about how they fit together. The process emphasizes high-conviction ideas across funds, making factors like holdings count, active exposure, and top-ten concentration crucial.NextFolio offers strategies across all nine Morningstar style boxes. The inception dates for each are as follows:
For the ensemble process to effectively capture high-conviction signals across funds, 10-15 strategies are the desired range. Too few funds lead to insufficient diversification on multiple levels, while too many funds overdiversify the number of signals needed to achieve effective ensemble construction.
NextFolio’s key differentiator is its focus on utilizing multiple funds and only high-conviction stocks across those funds to form portfolios. Unlike traditional firms that offer single-manager products, NextFolio's Ensemble Active process uses mutual funds as models to identify investment insights, focusing on high-conviction ideas as predictive signals.
Another major distinction is that NextFolio applies this approach across all nine Morningstar style boxes, a breadth few firms offer.Ensemble methods combine the strengths of individual models by leveraging their diverse perspectives. This approach:
It has, in areas like asset allocation and risk management, but not effectively or at all in stock selection. Historically, mutual fund holdings have been disclosed only with significant delays, making it difficult to apply this approach.
With proprietary new technology that provides real-time access to holdings and weights, Ensemble Methods can now be used effectively in portfolio construction.
© 2025 NextFolio. All rights reserved.