Alibaba Health Information Technology Ltd.
Equity · Monthly series · EQ-241.HKEX
Latest, October 2026
2.83 HKD
-1.4% from September 2026
Forecast
Forecast for October 2027: 2.59 HKD, with an 80% interval of 0.41 HKD to 7.53 HKD.
| Period | Forecast | 80% low | 80% high |
|---|---|---|---|
| November 2026 | 2.79 HKD | 2.18 HKD | 3.69 HKD |
| December 2026 | 2.73 HKD | 2.23 HKD | 3.56 HKD |
| January 2027 | 2.71 HKD | 1.66 HKD | 4.61 HKD |
| February 2027 | 2.68 HKD | 1.48 HKD | 4.94 HKD |
| March 2027 | 2.66 HKD | 1.39 HKD | 5.18 HKD |
| April 2027 | 2.64 HKD | 1.08 HKD | 5.84 HKD |
| May 2027 | 2.63 HKD | 1.24 HKD | 5.62 HKD |
| June 2027 | 2.63 HKD | 1.12 HKD | 5.93 HKD |
| July 2027 | 2.62 HKD | 0.47 HKD | 7.35 HKD |
| August 2027 | 2.60 HKD | 1.04 HKD | 6.09 HKD |
| September 2027 | 2.60 HKD | 0.78 HKD | 6.73 HKD |
| October 2027 | 2.59 HKD | 0.41 HKD | 7.53 HKD |
AI confidence
Needs refreshThe data refresh is due. Confidence will be reassessed against the refreshed history.
Model: Agentic Investor TSFM (foundation model)
- Accuracy vs naive
- n/aNot evaluated
- Direction
- n/aNot evaluated
- Turning points
- n/aNot evaluated
How this assessment is made
AI confidence describes historical evidence for this forecast, not a probability of being correct. Each backtest fits on data available before its test window. The baseline carries the last value forward. Supported evidence requires at least six complete, non-overlapping tests, an error ratio below 0.90 (rounded to two decimals), and wins in a majority of tests. Ratios from 0.90 to below 1.10 are on par; 1.10 or above is weak evidence. Inconsistent wins produce mixed evidence. For a selected model, only the recent tests excluded from model selection determine this label. These are historical simulations using the available data, not a live trading track record; revisions and foundation-model pretraining can limit how closely they reproduce a past decision. Past performance can change.
Model comparison
5 of 5 models evaluatedModels are selected on older tests and evaluated on separate recent tests. All four classes completed their backtests.
Models tested
Agentic Investor TSFM scored lowest on the 6 older tests (1.11) and was chosen. The 6 recent tests played no part in the choice and give its grade (0.91). The search for a model that beats the naive forecast on both sets of tests goes on. Scores are MASE: a model's errors divided by the naive forecast's, so 1 is a tie.
4 model classes completed the tests: Foundation model, Machine learning, Statistical, Neural network.
| Model | Class and compute | Older tests | Recent tests | Role |
|---|---|---|---|---|
| Naive forecast (last value held) | Benchmark · CPU | 1.00 | 1.00 | Benchmark |
| Timestral (foundation model) | Foundation model · CPU | 1.11 | 0.91 | Serving |
| ci-proto (foundation model) | Foundation model · CPU | 1.22 | 0.88 | Tested |
| CatBoost (machine learning) | Machine learning · CPU | 1.23 | 1.05 | Tested |
| AutoETS (statistical) | Statistical · CPU | 1.30 | 1.88 | Tested |
| N-HiTS (neural network) | Neural network · CPU | 1.36 | 3.17 | Tested |
Reading
That is the lowest of the 120 readings since November 2016.
Recent history (24 observations)
| Period | Value |
|---|---|
| October 2026 | 2.83 HKD |
| September 2026 | 2.87 HKD |
| August 2026 | 3.09 HKD |
| July 2026 | 3.59 HKD |
| June 2026 | 3.08 HKD |
| May 2026 | 3.63 HKD |
| April 2026 | 4.37 HKD |
| March 2026 | 4.66 HKD |
| February 2026 | 5.58 HKD |
| January 2026 | 6.52 HKD |
| December 2025 | 5.05 HKD |
| November 2025 | 5.57 HKD |
| October 2025 | 5.80 HKD |
| September 2025 | 6.66 HKD |
| August 2025 | 5.46 HKD |
| July 2025 | 4.88 HKD |
| June 2025 | 4.74 HKD |
| May 2025 | 4.53 HKD |
| April 2025 | 5.04 HKD |
| March 2025 | 4.71 HKD |
| February 2025 | 5.01 HKD |
| January 2025 | 3.61 HKD |
| December 2024 | 3.32 HKD |
| November 2024 | 3.65 HKD |
Source
Data: public market data feeds.
More from Agentic Investor
- Open Alibaba Health Information Technology Ltd. in the app: the interactive chart and a fresh forecast
- World and commodity series: every stored series
- Vietnam indicators