top of page
Search

THE STOCK MARKET IS RIGGED: G-101 SPM AI algorithm


     These  result  cannot  be  true  unless  the “game is rigged”
     These result cannot be true unless the “game is rigged”

Prior to the development of the G-101 SPM AI algorithm, it was generally assumed that the equity market, where company shares are traded and safeguarded by anti-fraud regulations, was inherently fair. However, after extensive beta testing over many years, it has been observed that the stock market may not function on an entirely level playing field. This conclusion was reached during our latest iteration of the G-101 SPM AI algorithm when stock-picking accuracy ratings surpassed 85% on the last 2000 transactions.

  These result cannot be true unless the “game is rigged”

  --- not all of the time, but enough of the time to allow

  our algorithm to fair out the truth. Considering

  this single factor is unlikely that anyone

  is "right" 50% of the time, let alone

85% of the time.

Market predictions are intrinsically uncertain: The stock market is influenced by numerous factors, including economic indicators, political events, investor sentiment, and unforeseen episodes. No model or algorithm can account for every variable. Each circumstance has a hidden agenda that’s ripe for the taking. While some individuals or strategies might outperform others, success is often more about consistent long-term investing and risk management than about being right on every prediction. 

 Stock market manipulation can be classified under the following Events and involves artificially influencing the price of securities for personal gain, typically through deceptive and illegal practices. 

 The Events are:

  1. Spreading False Information: This involves disseminating untrue or misleading information about a company or stock to influence its price. Examples include "pump and dump" schemes (inflating a stock price with false positive information and then selling) and "short and distort" (spreading false negative information to drive down the price and then buying). 

  2. Manipulating Trading Activity: This involves creating artificial trading volumes or price movements. Examples include "spoofing" (placing and canceling large orders to mislead the market), and “wash trading" (buying and selling the same security to create the appearance of activity).

  3. Insider Trading: This is the illegal act of trading a public company's stock or other securities while having non-public; material information about the stock. 

  4. Cornering the Market: This involves “stock bullying” (gaining sufficient control over a particular asset or commodity to manipulate its price). 

 G-101 SPM AI algorithm cannot anticipate stock market manipulations, but it can identify the characteristics after the “event” occurs. We call it, “wave riding after the fact.” Buying in or selling out of the anomaly.

 THE ANOMALY IDENTIFIER IS THE SPM TAG

 Currently, the G-101 SPM AI algorithm has 145 data subsets organized into a single column. Each data point is assigned to a value-weighted component that reflects its relative importance and accuracy. This means some data points contribute more significantly to the overall average or calculation than others. Once compiled the value-weighted data column is measured as a single entity within a proprietary validation matrix that creates a time-sensitive, subjective probability model (SPM) tag value.

The algorithm can identify and track stock manipulations through data irregularities; can follow variations in trading patterns of schemers with low-latency data or insider information. These anomalies are predictable due to their repetitive and consistent structure, allowing for anticipation of a stock’s direction. Such predictabilities enable our algorithm to follow guidelines that disclose pattern creations and tendencies. By recognizing collective changes and repetitions between elements in the patterns, the platform is able to rate the reliability of such formations by applying a subjective probability model (SPM) tag value as a “best guess” conclusion score. i.e. A higher SPM tag value indicates a more reliable source of data.

Despite these complexity, schemers must reluctantly generate a paper trail to instigate the Event: This involves broadcasting fake or misleading investor data by generating trading tickets with timestamps, prices, volumes, origins, and handlers. Such activities are observable and accessible to some extent.

Ticket tracking is a significant proprietary component within the G-101 SPM AI algorithm, and its trigger is volume. Volume, in the context of stocks, refers to the number of shares traded during a specific time period, such as a day or a week. It's a crucial indicator because it provides insights into market activity, interest, and the strength of price movements. High volume often indicates significant market interest and participation, while low volume might suggest a decrease in market activity. Volume identifiers within the matrix can establish entry and exit points based on a subjective probability model (SPM). For instance, a high-volume breakout may indicate a buying opportunity, whereas a sudden drop in volume during a price decline may suggest a selling opportunity.  

After locking in volume identifiers, the algorithm assigns first-level SPM tags to stock targets and starts verifying paper trails. Each information component within the subset receives a numerical value based on the accuracy of the information stream. A “soft” value SPM tag is given to all collected data, combined with the volume identifier, and then assigned a second-level SPM tag. This secondary value is matched with at least 75 out of 145 subsets for a final SPM tag and classified as a prime-time investment candidate.

Market predictions are no longer exclusively

 technical and fundamental analysis

 Outsmarting the stock market, knowing that it's rigged, requires a new means of critical thinking with a full-range and semblance of linkable data.  It’s no longer exclusively technical and fundamental analysis but a combination of other types of data, more intuitive, stickier. Algorithms and machine learning have taken data exploitation to a level that seemed impossible just a few years ago. The result: We’re at the crossroad whereby investing is no longer an art like gambling, but a science.  

When dealing with “intangibles” i.e. common stocks, technical and fundamental analysis are not good enough to properly influence and safeguard investment decisions.  Classic Wall Street thinking is a lost and expensive art. Today, a new way of processing information is changing the investing landscape. Quantitative and qualitative research methods, user-centered design methodologies, interpersonal and problem-solving techniques are the non-human factors necessary to accurately evaluate and instantly apply information in making investment decisions.  

In conclusion, we cannot alter the rules or control access. Our solution is to adapt and leverage anomalies; that’s the essence of SPM TAGS - 'wave riding after the fact.'

 CERTIFIED SPM TAG RESULTS

 G-101 SPM AI PORTFOLIO REPORT CARD:

  • For the trading month ending, May 30, 2025, at 4:00 PM, 65 trades were posted of which 23 trades were closed out with 22 GAINS and one EVEN.

  • Our Accuracy Percentage Rating (APR) for the month ending May 30, 2025, was 100.00% versus 92.86% for the prior month.

  • From March 9, 2023, to May 30, 2025, a total of 2939 trades were posted with an APR of 89.05% versus 83.19% of the prior month. The net results are based on liquidated values and net gains (losses) of unrealized positions as of May 30, 2025, 4:00 EST.

All of the 2939 trades are documented by dates, timestamps and values at Stocktwits under G101SPM https://stocktwits.com/G101SPM. Click SEARCH (magnifying glass) icon on our landing page to review all trades and related data.

OVERVIEW OF G-101 SPM AI algorithm and its data subsets:

On March 9, 2023, the G-101 SPM AI algorithm was introduced with 129 subsets of data in a single column. By March 17, 2023, the certification process commenced by posting publicly accessible data through Stocktwits, an independent social media platform designed for sharing ideas between investors, traders, and entrepreneurs under G101SPM https://stocktwits.com/G101SPM. Additionally, three modifications to the algorithm were made: (1) On November 1, 2023, the G-101 SPM AI algorithm was modified to detect short-side anomalies by adding six new subsets to the database. The objective was to enhance our understanding of the stock buying/selling environment dealing with part-time investors’ trading habits and results.  The consolidated data shows that 92.24% of investors lose money in stocks. The conclusion --- part-time investing is a losing proposition.  The system calculated that 61.3% of   adults in the United States invested in the stock market, of which 37.7% are part-time investors. The new subset identified as "Sell side Factor 6 Subset" added a 1.74% increase to the algorithm’s accuracy on the next 1000 trades. (2) Effective February 1, 2025, 14 supplementary preset data sources were added to the value component of the G-101 SPM AI matrix. The modifications increased the subset to 143 from 129. The intent was for the systems to recognize and process a new set of challenges fostered by President Trump’s second term – includes changes to immigration policy, a spending freeze, tariff reforms and interrelated anomalies. Within the matrix the platform enhance the focus on fear, greed, regret, overconfidence, misinterpretation and generative hidden agendas. This subset identified as "Trump Factor #1” added a 3.94% increase to the algorithm’s accuracy on the next 1000 trades. (3) After March 15, 2025, two additional subsets were added to bring the total to 145 subsets. These propriety variances had no material improvement to the algorithm’s accuracy rating.  

 THE SECRET SAUCE IS THE

 SUBJECTIVE PROBABILITY MODEL (SPM) TAG.

 G-101 SPM algorithm is an investment/enterprise predictor that gathers data from 145 preset sources and presents the values as SPM TAGS. The database tracks over 5215 individual stock components and other data subsets with each one carrying a "floating" SPM tag. The higher the value the greater the subjective probability of the collective data being accurate. The performance-driven platform evaluates current and historical records; and is structured as a digital monitoring surveillance tool to solve and deter misinformation while managing a database to offer "best guess" solutions. Its main engine is the Primary Volume Locator (PVL) which continuously tracks cash flows of the S&P 500 Index components to establish a directional control grid. Once the algorithm is locked into that variable, the platform searches for stock anomalies and imbalances between supply and demand.

Only a third of the subsets are dedicated to fundamental and technical indicators. The balance of subsets are programed to track industrial and general economic data, investor sentiment, including emotions like fear, greed, and optimism, and overall market trends. Indeed, "market psychology," is the influential factor within these subsets. 

 SPM TAGS AND THEIR FUNCTION

SPM TAGS are proprietary external influencers within the Subjective Probability Model that collect, process, analyze and filter raw information into classified and structured data.  The cooked data is manipulated to function in unison with different data categories to integrate and analyze them in a more streamlined and efficient way by creating pre-computed aggregates and normalized tables called “tags.” This allows for faster querying and analysis of complex datasets that work together through various data integration techniques and allows for combined analysis and insights. These methods help combine data from disparate sources, providing a unified view for SPM tag analysis. 

We are able to separate the data into categories by using grouping variables. This involves identifying specific features and characteristics that define different groups within the data, allowing us to organize the data into factors that can affect decisions, behaviors, and outcomes.

Since investing in stocks is not purely a rational process, the data points relating to fundamental and technical analysis were too empirical. Informed decision-making requires other essential data and analyses that can improve investment strategies, such as.

(1) Quantitative Analysis: Utilizing mathematical and statistical models to analyze large datasets and identify trends and patterns that may not be readily apparent through other methods; the need to provide an objective, data-driven perspective and help uncover hidden opportunities or risks.

SPM subsets, 45, 46, 47, 48, 52, 53, 91 and classified as (i) factor-based models, (ii) algorithmic trading strategies, and (iii) statistical arbitrage. 

(2) Sentiment Analysis: Gauging the overall market mood, investor emotions toward a particular stock, sector, and the market as a whole.

SPM subsets, 18, 19, 20, 25, 27, 29, 44 are classified as (i) news articles, (ii) social media discussions, (iii) analyst ratings, (iv) overall public opinion to understand the prevailing sentiment, (v) news aggregators, (vi) social media sentiment analysis platforms.

(3) Macroeconomic Data and Analysis: (i) tracking interest rates, (ii) inflation rates, (iii) GDP growth, (iv) unemployment figures, (v) government policies. 

SPM subsets, 7, 8, 9, 14, 15, 34, 35, 106, 107, 111.

(4) Industry Analysis: (i) analyze industry reports, (ii) market research data, (iii) competitor analysis to assess a company's position (iv) future prospects within its industry. 

SPM subsets, 112, 113, 114, 115, 116, 122, 124, 125, 134, 141.

(5) Company Management and Qualitative Factors: (i) evaluating the quality and track record of the company's management team, (ii) brand reputation (iii) corporate governance, (iv) review management biographies, (v) company press releases, (vi) investor relations materials to assess the quality of leadership. 

(6) Holistic Factors: (i) unpredictable events (like market crashes or political instability).

SPM subsets, 71, 72, 86, 87.

(7) Anomalistic Faction: (i) Walmart gauge how American consumers are faring. SPM subset 42; (ii) Productivity rates and economists’ expectations, SPM subset 82.

 SPM TAG RATING 1/ SCORES

 ON THE LAST ONE THOUSAND PICKS

The higher the SPM tag the more likely the success of “best guessing” a stock’s future value.

SPM 92.62 tag to SPM 87.00 tag are correct on a weighted average 88% of the time.

SPM 86.99 tag to SPM 81.99 tags are correct on weighted average 83% of the time.

SPM 81.98 tag to SPM 75.00 tags are correct on a weighted average 77% of the time.

SPM 74.99 tag to SPM 65.99 tags are correct on weighted average % of the time.

SPM 64.00 to tag SPM 59.99 tags are correct on weighted average 57% of the time.

SPM 59.98 tag to SPM 50.00 tags are correct on weighted average 54% of the time.  

1/ Current rating configuration

 G-101 SPM AI ALGORITHM, AN ANALYTICAL DOTBOT,

 SURPASSES OTHER AI MODELS IN SELECTION ACCURACY.

 The rise of generative AI (GenAI) models, like OpenAI’s GPT, have accelerated our transformation. In the process, we have become Number One in non-human investment/enterprise analytics. Our tools do more than process data, G-101 SPM AI generates world-class content, fully automated workflows, and unlocks insights in ways traditional AI applications may have difficulties in matching. 

Other AI platforms work on approximations and are less reliable than random stock picks. Contemporary stock investment AI models lack emotional intelligence, human discernment, creative problem-solving, and critical thinking skills. As stated, our secret sauce is the data: 145 subsets all functioning as a single column to prove and disprove the information by abstraction, substitution and value enhancement with “best guess” scenarios. Other AI systems are fallible and produce inaccurate outcomes because its data is trained on biased or limited datasets. When data is messy, incomplete or just plain bad, the output is not organized, structured and high-quality. Hallucinations to problems in the data results in uneven conclusions. For example, ChatGPT can "hallucinate" on fabricated information, meaning it can produce answers that are factually incorrect or nonsensical, even if they sound plausible. This happens because AI models don't fully understand the meaning of words or have the ability to reason logically about the correctness of their answers.  

Our information input is supported with over ten years of data diversity and sequential purging; retrieval-augmented generation (RAG) and incorporating user feedback into our model’s evolution. Filtering inaccurate or fabricated information is our mission, since our algorithm is programed on the premise that the stock market is rigged. As an information processor with conclusions, the algorithm functions like a detective with a focused agenda to prove that non-human intervention by our algorithm, an analytical dotbot, is far superior in evaluation data as to its accuracy.


 That’s it! Our story.

 G-101 is unparalleled, as proven by our results.

 “Sometimes in life the glass seems half empty, sometimes it seems half full, and sometime the glass is twice as large as it needs to be.”

 That’s how Wall Street is – our algorithm functions on a simpler proposition: Find the anomalies and trade the noise.

 We call it “ride the wave.”

 Is the Stock Market rigged?”

 So what! That’s for another day.



  "Making big money in a rigged market is a science. Let us show you how."


Allow G-101 SPM AI algorithm to be your financial guide.

 

 
 
 

Comments


Newsroom

bottom of page