What we do:
Fine-tuned Technical Indicators through Iterative Back-testing

AGNO has one goal: Provide more information to people that actively invest in the stock market. Broadening their possibilities so that trading becomes easier. We bring the power of data analysis to give investors more clarity about which variables or strategies to use in their daily operations.


Why our reports are worth buying?

We combine modern computer-based simulation technologies and financial knowledge to fine tune investment strategies that are easy to implement in your current trading platform.

Modern technologies applied to finance

Statistical Validation

Alternatives for Investors

Economic Product

Still lost about what we do? Check out this video!

Agno does back testing simulations with a myriad combination of variables regarding a specific investment strategy. Our goal is to produce a set of variables that have a good chance of producing positive trading results.

Check out our blog

29 May: Performance Report – Relative Strength Index (DIS) – 5/29/2020

Strategy = Relative Strength Index Stock = Disney (DIS) Performance (YTD) -> Strategy (11.54%), Buy and Hold (-19.84) and VOO…

28 May: Performance Report – Relative Strength Index (AAPL)

Strategy = Relative Strength Index Stock = Apple (AAPL) Performance (YTD) -> Strategy (2.89%), Buy and Hold (8.88) and VOO…

20 Mar: Monthly return simulation for S&P 500 Index – (Monte Carlo Simulation)

AGNO focuses on producing investment strategies for active trading which is a high risk/reward approach. I am conscious that not…

Creator and Owner:
Daniel Agredo Sarria

Industrial Engineer | MS in Finance

Skillful Quantitative Analyst with experience in equity research, valuation and financial analysis. Effective user of modern programming languages (Python – R) to perform data analysis, forecasts and statistical models. Creative and relentless problem solver with a keen sense of curiosity towards optimizing, fixing and improving professional and everyday life situations.


Methodology that evaluates how a particular investment strategy performs in past data. At Agno we perform a substantial number of back-tests to build our reports.

Methodology that tries to predict future price movements from past data behavior and/or market statistics (indicators). At AGNO we select popular technical indicators and fine tune them by using iterative back testing.

Technical indicators usually come with predetermined/suggested variables that traders use for all securities in their watchlist (e.g. RSI usually uses 14 periods, 30 as oversold and 70 as overbought). At Agno we believe that each stock is unique and therefore tailored indicators are needed to trade more accurately. After many tests we have found that commonly used variables in popular indicators do not perform as well as other combinations.

After running thousands of back tests for a specific investment strategy, it is chosen the set of variables that aggregate more probability towards positive results. The outlier set of variables that have incredible returns is not considered due to overfitting concerns. We aspire to deliver indicators that often deliver good results rather than a one trick pony.

Absolutely not! We only write a report when we find substantial evidence that it may work forward. However, bear in mind that we work with probability and estimations and therefore the risk of negative returns is still present. Please refer to our disclaimer for more information on this matter.

Drop Us A Line

A very simple example

Strategy: Simple moving average crossover. A set of two simple moving average of closing prices. One “Fast” with a shorter period and one “Slow” with a larger period. Usually traders use 20 and 40 as variables. But are those variables ideal for every stock?
Range of possible variables: N1= {5,6,7, …, 30} and N2= {40,41,42, …, 80}

Methodology: Our code takes these ranges and performs a Back test for each combination. In this case it would be 1,066 iterations. We create histograms and box plots to better understand the data and then choose the set of variables that amass greater probability of positive results.

Our final product: We provide a summarized report with our chosen variables for a specific trading strategy applied to a specific stock. We do not believe in universal indicators that work for any stock.