My name is Rosh, and like you, I have a story of struggle and success. Creating an algorithm that consistently correlates to the next day’s market open is about as easy as discovering the meaning of life (I’m working on both). I’ve always enjoyed sharing what I learn and helping people improve their lives. This project is no different.
This is a randomly, casually updated history of SPYtomorrow.com development.
Here we go…
In the early 2000’s I taught myself how to buy and sell stocks and options with a small online account. At the time, I learned a lot about the stock and options markets, yet had little success due to the size of my positions and the tax of broker commissions.
The Downfall
Like many in 2008 and 2009, I discontinued my trading as my financial world came tumbling down. Many faced a great recession, and in Detroit, we faced a Depression. To pull my family out of ruin, I refocused my energy on my creative entrepreneurial media career.
Over the next few years, I clawed my way back, yet I lost everything again in 2013/14. I was forced out of a business I helped build, my teaching positions ended, and I went through a divorce.
Rebound
Eventually, I married again and rebuilt my entrepreneurial career from the ashes. I vowed never to let outside forces decide my future again.
At the beginning of the new year 2020, my wife, our family, and I became comfortable in our lives and careers. Upon reviewing the past, I realized I hadn’t seriously started saving again for the future. I’m much older now, and if I want to retire, I need to save more aggressively.
I dusted off my 20-year-old account—which, believe it or not, was still active. My plan was to use my stock-picking skills to invest in our future. I made my first trade and noticed something amazing: no commission! With the advent of free trading platforms such as Robinhood (not a recommendation), larger brokerages began offering no/low commission trading.
The Financial Experiment
As an experiment, I started aggressively testing some of my old trading ideas from twenty years ago. With the volatility of early 2020, I made 50% on my new small Roth account in my first month.
However, I had questions. Some trades didn’t go as expected, and I wanted to figure out why. I began randomly using data I found online to create calculations to help me understand why certain things were happening, especially in the options market.
Over time, through testing and observation, I discovered the first market indicators that I trusted. These two indicators work together: one I referred to as the call mood (for positive market pressure) and the other as the put mood (for negative market pressure).
I originally implemented QQQ data into my calculators and later experimented with other ETFs with success. However, I realized each ETF was a little different, and the calculators needed to be calibrated accordingly. So, I settled on SPY (S&P 500) as my main indicator.
Eventually, through additional experimentation, I discovered another indicator that was quite accurate—a secondary support indicator I called the Pressure 3 indicator.
After a couple of months, I decided to try to double $1000 in a month using my SPY calculator. Instead, I tripled the money, turning $1000 into $3000 in about 3 weeks using directional options trading.
Adjustments
Not long after, I noticed my trades weren’t going very well. As market volatility calmed in the summer of 2020, my readings were more often mixed. I would make educated guesses, but a flat market isn’t ideal for some types of options trading.
My calculator, which averaged over 80% correct, dropped into the low seventies. Still, even when the calculator was right, losses occurred due to a lack of volatility and premature stop-outs during market reversals. This is a risk inherent in trading stocks and options, but it was especially pronounced during this period. I lost a couple of thousand dollars of my previous profit.
After reviewing my summer trades, I realized that when my calculator showed mixed signals, it was essentially a 50/50 shot as to the next day’s market direction. Often the market starts off flat—which is valuable data—but not conducive to my preferred trading style.
Once I disciplined myself to avoid trading on mixed-signal days and volatility increased, profits began to return.
New Signals
During the end of my summer vacation in 2020, I decided to backtest and search for even better indicators. I discovered some promising candidates, though most weren’t as solid as the ones I already trusted. One indicator did stand out, and I began incorporating it into my trading—the G 100 indicator (no longer used).
By the end of summer, when all indicators pointed in the same direction, they averaged 80%-90% accuracy. With renewed confidence, I launched spytomorrow.com.
Yet, by the end of September 2020 and the beginning of October 2020, many signals began showing doom and gloom. Although I initially performed well, low volume up days set in and the indicators faltered—resulting in a period of losses.
Try Again
Back to the drawing board—I reviewed my trades, reworked formulas, and tested old ideas. Eventually, I discovered a solution that met my three criteria: stability (minimal fluctuations), no need for interpretation, and zero calibration.
After a few semi-successes and failures during a challenging October, I refined my approach. I expanded the solution into what I now call the SPY Waves: SPY 2 Wave (S2W), SPY 4 Wave (S4W), and SPY 6 Wave (S6W)—collectively known as N Waves.
As volatility decreased, some Waves broke down; however, the N2 Wave and The VV Wave maintained 80% accuracy even during the calmest periods. Combining parts of these calculations (N2VV) yielded about 90% accuracy—until it later settled to 80%. When all three were combined, I finally achieved the indicator I was seeking.
As of January 4, 2021, I began using the 3 Wave indicator for my front page predictions, with additional insights available to members once membership reopened.
By mid-January 2021, a better dataset improved the accuracy of my Wave calculations. Starting January 14, 2021, I began sharing prediction charts on the front page alongside the pressure prediction for a more complete picture.
I’ve declared my calculations final several times, yet unpredictable “switches” would emerge—forcing further refinement.
By late February 2021, I found stronger methods for capturing and interpreting data, declaring my final version of spytomorrow. I knew then there was no further refinement possible.
March 2021 proved tumultuous due to major market news, prompting one final attempt. I revisited my original successful formula, integrated everything I had learned, and created new waves back-tested with solid results.
I officially launched the C Waves (CBN) on March 29th. After a year of refining these formulas, I launched spytomorrow.com membership in September 2020—only to later refund subscriptions when issues persisted.
I spent the summer of 2021 addressing the problematic switches. With a broader view of market data, I refined my calculators and improved my trading skills, leading to increased profits on the correct days.
With a new global data approach, I was able to reimplement some of my previously successful SPY calculators, now understanding why they had failed.
Testing for the Third SPY Open
Beginning November 1, 2021, I ran the third beta of SPY Tomorrow with new calculations and switches. After three months, the everyday calculator was over 80% correct, and the strongest signals reached about 90% accuracy—though not every day produced a complete signal.
I then started posting the strongest signals on the front page. When membership reopened, additional signals were provided to guide the next day’s direction.
My goal was to complete 100 trades with successful outcomes before reopening membership.
Unfortunately, chasing shiny new ideas led to a poor December. Recognizing the error, I finalized my calculation approach and delayed membership until February 2022, when the third beta performed well.
WAR and Inflation
The launch of the new membership option coincided with war and rising inflation. Although there were more incorrect days than usual, SPY maintained stability—it was the overnight market mood that shifted due to news. Fast new cycles aren’t ideal for overnight trading.
SPY performed as expected, allowing me to focus on improvements rather than fixing a broken system—a process that continued over the last two years. The solution to the switches I began working on in August 2021 remained robust.
During early 2022, I improved calculation speed significantly. What once took 12-15 minutes now took about a minute, freeing up time for insights. In mid-February, I began offering QQQ and IWM pressure readings to members, strengthening overall predictions.
By April 2022, I expanded my triangulation approach, increasing data columns from 3 to 9 for members who wanted to explore their own patterns. Though the data looked complex, it offered deep insight.
Next, I color-coded algorithm sections into Purple, Orange, and Blue (POB). Blue, the August 2022 combination, performed best. I also added large prediction numbers and visual arrows (green, yellow, neutral, orange, red) for clarity.
Game-Changing Insight
I experimented with multiple triangulations and discovered that higher combined plus/minus totals (ranging from -27 to 27) correlated with better prediction accuracy. This became crucial for position sizing: lower totals meant smaller trades, higher totals justified larger ones.
Even Better Triangulation
By mid-April, I refined the visual presentation and began incorporating IWM and QQQ data to help determine the SPY trade. For example, if SPY was -1, QQQ +3, and IWM +10, I could cautiously predict an upward move in SPY. This method improved accuracy by preventing over-reliance on lower SPY numbers.
By June 2022, I adjusted my approach for confidence readings—numbers 9 and above were nearly 100% correct over two months. I also began purchasing data (instead of relying solely on free sources) to expand my services.
In July 2022, I experimented with AI to analyze my data, which led to developing the MPI (Market Pressure Index). Although early attempts were overambitious, reexamining older algorithms led me to reintroduce the effective Yellow series.
Also in July 2022, I explored directional hedging strategies in SPY-T trading and hosted a webinar on July 20, 2022, to share my insights.
Membership grew, and sustained subscriptions indicated that members valued the SPY-T signals.
Algorithm Update and Daily Pressure
In fall 2022, the spring/summer algorithm slipped below 70% accuracy amid strong membership growth. Much of this surge came from the spytomorrow YouTube channel. By December, with new features like hourly pressure updates being tested, I paused for mental health reasons.
I made necessary adjustments, removing a consistently positive Blue section from the 2023 update to improve accuracy.
The Heart
After an initially strong launch, early 2021 saw a decline in accuracy. I restructured my approach from using 3, 9, or 27 data points to 81—a model I call “the heart.” After back-testing over 160 trades, the heart averaged 75% accuracy. Although some months varied, this became my benchmark.
I introduced new waves—SPY 2 Wave (S2W), SPY 4 Wave (S4W), and SPY 6 Wave (S6W), collectively called N Waves. These adjustments, along with my “red heart” concept, were refined as I managed volatility and data issues.
Hearts Breaking (August 29, 2023)
Despite early success, the Red and Yellow hearts faltered. I updated the heart model—likely transitioning to a Purple version—as the Yellow boards led to a new direction (and the Orange algorithms and current Purple series emerged). The MPI era is currently on hold.
The Purple series now compares the 3 PM reading to the 3:48 reading, similar to the N2VV method. While early results were promising, a switch in the data affected signals. The latest Purple Max appears to account for this, and further refinements continue.
Purple Update: (October 14, 2023)
The Purple series is performing well. The Purple Max I is the public up/down signal, averaging 80%-90% accuracy over the last 61 days. Its performance gives me confidence for the new year.
Purple Success Continues April 2024
As of April 2024, the Purple algorithm—using the Max I calculation—remains the longest-running method since the inception of SPY Tomorrow. Small tweaks have been made, but the core algorithm still averages around 75% correct. This success has allowed me to focus on new probability numbers and additional support measures for members.
After more than a year of reliable performance from the Purple algorithm, I set out in November 2024 to overhaul the site with smarter systems and richer features. I thought it would take only a couple of months, but when the new Blue algorithm officially launched on April 2, 2025 (yes—skipping April 1 was intentional) the rollout hit a few bumps (disaster). I spent the following weeks fixing those issues, and by mid‑May the platform was not only stable but noticeably more powerful.
On July 31, 2025 I retired the manual‑heavy Purple algorithm—not because it failed, but because advances in AI‑assisted coding made Blue a fully automated, higher‑performance successor.
January 2026Through the rest of the year, I refined my new algorithms and eventually launched the Gold series January 2, 2026. This also includes the CV Engine which is similar concept and lessons learned developing the heart algorithm
Next up: additional sites dedicated to other ETFs, starting with QQQ, IWM, and IBIT. Stay tuned for more tools designed to give you insight.
My goal is to empower as many people as possible with high‑quality information that boosts their probabilities of success in overnight swing trading, enabling them to generate additional income for their families, communities, and charitable causes.