An interactive guide to the algorithmic trading research platform — from searching a ticker to ML-powered predictions, explained simply.
Explore the WorkflowStockVisionz follows a clear pipeline. Each step feeds the next — nothing is skipped, nothing is guessed.
User types a ticker
Pull price & news data
Calculate indicators
Run ML models
Walk-forward testing
Dashboard results
Press the button below to simulate what happens when you search "AAPL" — step by step.
The frontend sends a request to the backend API
If new → full backfill from 2016. If existing → fetch only missing days.
Open, High, Low, Close, Volume — stored in time-series database
RSI, MACD, Bollinger Bands, ATR, moving averages — all saved
Alpaca News API + FinBERT scores each headline positive/negative
Combine price + indicators + sentiment into one table for ML models
Job queued → Worker picks it up → Walk-forward validation runs
Accuracy, Sharpe ratio, equity curve — compare all models side by side
Let's unpack what's happening at every step of the pipeline.
When you search a ticker, the system pulls years of daily price data from Yahoo Finance — the entire trading history downloaded into our database.
Raw prices aren't enough. We compute mathematical indicators that traders use to spot momentum, trends, and volatility patterns.
All indicators and price data combine into a single table. Each row = one trading day. Each column = a signal the model learns from.
Click "Train" and a job enters the queue. A background worker picks it up and trains the model. You see progress in real time.
We test exactly how a model would perform in real life: train on the past, predict the future. The window slides through time.
Interactive charts, ML experiments, backtesting, news sentiment, and drift monitoring — all unified in one dashboard.
Trace a request from your search to live results. Each color is a layer.
"Will this stock go up or down tomorrow?" — each model takes a different approach to answering it.
Simple linear baseline
BaselineClassic up/down classifier
BaselineFinds the best boundary
TraditionalVotes from many trees
TraditionalGPU-powered boosting
GPU RequiredDeep learning sequences
Deep LearningRL agent learns to trade
ReinforcementPolicy gradient agent
ReinforcementActor-Critic agent
ReinforcementAll 9 models train on the exact same data splits — same dates, same windows. They share a comparison group ID so you can view them side by side.
Train on the past, test on the future, slide forward. This is how the model would actually be used in real life.
Each row is one "fold." The window slides forward by 21 days each time, so the model is always tested on data it has never seen — exactly like real trading.
The #1 risk in stock ML is "data leakage" — accidentally letting the model see the future. These 6 automated checks run on every single training job.
Training always ends before testing starts, with a purge gap in between.
All features shifted by 1 day — the model never sees "today's" data when predicting tomorrow.
The prediction target is confirmed to be the next day's actual result — no future information leaks in.
Data normalization fit only on training data. Test data is never used to compute the scaler.
Database queries validated — no row from the future sneaks into the training set.
Test sets across different folds never overlap — no data point is tested twice.
The tools and frameworks powering StockVisionz.