Telegram RegisterThe public register of Telegram

Channel

ML for Value / Ваня Максимов

@ml4value

On this record: Growth · Engagement · What this channel posts · Reactions · Stars · Posts · Telegram's recommendations · Cite this entry

5,711subscribers

+0 since we began measuring on 7 August 2026

Risers and fallers across the register · movement among entries of 3,162–10,000.

Register entry

Telegram ID-1001427782022
TypeChannel
Username@ml4value
DescriptionПуть от ML-модели до Value для компании | RecSys, Search, LLM, Pricing и CLTV Ваня Максимов, @Ivan_maksimov Head of AI | Recsys, search, llm @Y.Market, ex-WB, ex-Delivery Club Консультирую компании, Веду курсы Публикую релевантную рекламу
CreatedBetween 1 April 2019 and 31 August 2021— estimated from Telegram’s id allocation, not measured. How this range is calculated.
First recorded7 August 2026
Last confirmed live10 August 2026
Measurements held2
Confirmed unchanged2 times, most recently 10 August 2026
On Telegramt.me/ml4value

Growth

5,7117 Aug 2026, 02:02 — 5,711 subscribers7 Aug 2026, 16:53 — 5,711 subscribers7 Aug 2026, 02:027 Aug 2026, 16:53
2 measurements taken within a single day. Dots are measurements; the straight line between them is drawn to join them, not to claim we know the path taken in between — snapshots are recorded only when a count changes, so gaps mean “no change observed”, never “interpolated”. The vertical axis spans 5,705–5,717 and does not start at zero.
Measurement log — every subscribers count we have recorded
Measured (UTC)SubscribersChange
7 Aug 2026, 16:535,711no change
7 Aug 2026, 02:025,711first reading

Engagement

8 posts held, back to 9 January 2026the reader has not yet reached the start of this channel’s public history, so older posts may sit further back, unread. Read across 8 pagesof Telegram’s post history, 20 posts per page.

Nothing published in the last 30 days. ERR and ER are rolling 30-day measures, so there is nothing to compute — we hold 8 posts for this entry, the most recent from 12 June 2026. An engagement rate over an empty window would be a number about nothing.

What this channel posts

Photos
216
Videos
1
Links
123

Lifetime counters from Telegram’s own channel header, read 12 August 2026 — not the date at the top of this page, which is when the subscriber count was last read. Below Telegram’s rounding threshold, so these counts are exact.

Reaction mix

379 reactions across 8 posts, in 10 distinct kinds. The most used accounts for 47.2% of them.

Every reaction kind recorded on the sample, most used first
ReactionCountShareShare, drawn
17947.2%
👍10226.9%
🔥7519.8%
👎82.11%
51.32%
🗿30.792%
😁30.792%
💅20.528%
😎10.264%
😱10.264%

No sentiment is inferred, and none should be read in. This table is ordered by count and by nothing else. Emoji do not carry stable meaning across languages or communities — 🙏 is thanks in one channel and mourning in another — so we publish which ones were pressed and how often, and pass no judgement on what an audience meant by them.

Precision. Telegram publishes reaction counts per emoji and short-forms each one — 4.34K, 1.2M — so any single kind at or above 1,000 reaches us at three significant figures, and only counts below 1,000 are exact. The shares above are ratios of those figures and carry the same error. This is also why the total here can differ slightly from a reaction total printed elsewhere on the page: both are sums of the same rounded parts, taken over samples with different edges.

Coverage. Reactions were read on 8 of the 8 sampled posts in this sample. Summed by Telegram’s own count on each post — not by adding up the per-emoji breakdown above — those same posts carry 379reactions in total: the kind of figure the paragraph above means by “a reaction total printed elsewhere on the page”.

Measured over the 8 most recent posts we hold, published 9 January 2026 to 12 June 2026, using the newest reading held for each. Telegram Stars are excluded: they are a payment, not a reaction, and they have their own section.

Telegram Stars

Stars received
2
across the posts below
Posts paid on
2
of 8 we hold a reading for · 25%
Most on one post
1
single highest reading

A paid reaction is a reader spending Telegram Stars — bought with money — on a post by @ml4value. Telegram publishes the count on the public post preview alongside ordinary reactions, and this register reads it there. It is the only figure on this site that measures money moving rather than attention.

Stars are not reactions, and the two are never added. They are rendered in the same strip on Telegram and counted in the same shape, but one is a tap and the other is a purchase. The reaction totals and the engagement rate elsewhere on this page exclude every figure in this section, and no rate here is computed against a reaction count.

This is not revenue, and we publish no currency figure. What a Star costs a reader and what it pays a channel are different numbers, Telegram takes a share we cannot observe, and the terms have changed. Converting a Star count into money would be an estimate dressed as a measurement, so the count is where we stop.

Counted over the 8 most recent posts we hold for this entry, published 9 January 2026 to 12 June 2026. Star counts above 1,000 reach us in Telegram’s short form and carry the same three-significant-figure rounding as everything else on this page.

Recent posts

12 Jun 2026, 11:46 UTC≈2,110 views46 reactions1 Starread 12 August 2026

The art of a strong baseline За последнее время все чаще понимаю, что создать сильный бейзлайн - это не просто база, с которой нужно начинать любой ml/ai продукт, а прям полноценная часть системы. Даже когда в проде уже давно есть трансформеры и агенты, бейзлайн дает прям много метрик Вот учите вы трансформер для персональных рекомендаций (sasrec, argus, pinnerformer, hstu - неважно). И если в лоб его применить, то

👍2910🔥7

2 May 2026, 08:04 UTC≈2,920 views82 reactionsread 12 August 2026
Photo

Начинать писать после перерыва всегда непросто, поэтому пока легкий пост про мои новости) Официально стал частью Transactional AI в Яндексе 🤖 Помимо персонализации всего в Я.Маркете буду делать ИИ-агентов для покупок товаров Съездил на теннисный турнир Barcelona Open 🎾 Мой первый турнир в качестве зрителя - это конечно топ! В полуфинале Рублев был крут, но и восходящие звезды Фис и Ходар впечатлили. Теперь еще боль

50👍21🔥11

29 Mar 2026, 09:21 UTC≈3,660 views14 reactionsread 12 August 2026
Photo

LLM - велосипед в новой обертке Холиварный пост выходного дня) Доля правды в этом есть - и это наоборот круто! LLM научились довольно неплохо решать в zero shot режиме (без обучения на доп данных) классические задачи: - Классификация текста - Named entity recognition (NER) - Суммаризация текста - Question answering по тексту (хотя тут еще есть куда расти) Куча бизнес-задач = комбинация нескольких таких простых к

👍7🔥4😁3

27 Mar 2026, 08:07 UTC≈3,120 views19 reactionsread 12 August 2026
Photo

LLM долгосрочные интересы пользователя Понемногу LLM-ки находят полезное применение в рекомендациях! Обычная реком система упрощенно устроена так: - Модель на короткой realtime истории пользователя (SLIM, SASRec, …) вытаскивает товары текущего интереса - Модель на очень длинной offline истории пользователя (часто ALS, LightFM) вытаскивает некие долгосрочные интересы - Их результаты смешиваются и переранжируются Ес

8👍6🔥4😎1

5 Feb 2026, 11:12 UTC≈3,690 views36 reactionsread 12 August 2026
Photo

Не проводи АВ-тест, пока не прочитаешь этот пост Да-да, это кликбейтный заголовок) Остановись на минутку. Вероятно, прямо сейчас у тебя идет какой-то АВ-тест. Вот скажи, зачем ты его проводишь? Вроде понятно, что это нужно для честного замера метрик. Но зачем их честно замерять? Попробуй ответить на несколько подряд идущих "Зачем?" Не только же для аналитического удовольствия мы АВ-тесты крутим 😅 А зачем нужны АВ-

16👍9🔥6🗿3💅2

16 Jan 2026, 07:34 UTC≈4,010 views51 reactions1 Starread 12 August 2026

Middle+ ML engineers ко мне в команду рекомендаций Я.Маркета (3 вакансии) 300-400к руб на руки Москва, Спб или remote *если вы senior - тоже пишите, договоримся) Наша команда рекомендаций Яндекс.Маркета делает персональные рекомендации товаров на главной странице, подбирает похожие и сопутствующие товары, персонализирует поиск, crm-коммуникации и другие поверхности. Мы - бизнесовая команда, которая приносит прямой п

🔥2812👍10😱1

15 Jan 2026, 09:16 UTC≈2,830 views18 reactionsread 12 August 2026

[3/3] Тщетные надежды и мечты Очень надеялся, что в рексис или поиске будет прорыв в этих темах в 2025, но он пока не случился 1. Economic recsys research А именно, внятное объединение recsys + pricing/promo в единую систему Даже в самом простом виде: продавец дал скидку 30%, но в кандидаты товар чаще попадать не стал, тк обычные двубашенный кандген ничего про скидку не знает В более сложном: мы можем сами давать

🔥15👍3

9 Jan 2026, 09:36 UTC≈3,440 views113 reactionsread 12 August 2026
Photo

[2/3] Продуктовые изменения в мире recsys & search и около них за 2024-25гг Больше про маркетплейсы, такая уж специфика у меня 1. VR-примерка одежды у крупных продавцов (Zara, ASOS) Наконец-та! Убийца маржи всех маркетплейсов (особенно fashion) - возвраты. Если их заметно снизить, то ecom вполне может совсем уничтожить оффлайн-магазины Обычно возврат идет после «примерки» одежды или товара в интерьере. В 2025 поя

83👍17👎85

Showing the 8 most recent of 8 posts we hold for @ml4value. View and reaction counts are the latest single reading for each post, not a live figure, and a recent post is still accumulating both. A view count marked was rounded by Telegram before we ever saw it — t.me prints views in full below 1,000 and to three significant figures above, so ≈1,200,000 means somewhere between 1,150,000 and 1,249,999. Unmarked counts are exact. Text is reproduced from the public post preview and truncated for length.

Stars beside a post are paid reactions — Telegram Stars, bought with money and spent on that post. They are a different unit from reactions and are never added to them, here or anywhere else on this page.

Appears in Telegram’s recommendations for other channels

The reverse of the list above, and a different kind of signal. This does not require this channel to have ever been asked about directly — each row below is a channel we DID ask Telegram about, whose Telegram-generated list happened to include this one. A channel can appear here with an empty list above it, because being named by someone else’s query is independent of having been queried itself.

Machinelearning
@ai_machinelearning_big_data · 286,250
Telegram ranks this channel #62 of 95 here — alongside 94 others — read 10 August 2026

This channel appears in 1 seed channel's Telegram-generated recommendation list in total. Each is Telegram’s list for THAT channel, not this one — see how this is measured.

Cite this entry

A live page changes as we take new readings, so a citation should name the measurement it is based on, not just the URL. The line below cites the subscriber count as measured 7 August 2026 — this entry's latest reading, not the date you are reading this.

“ML for Value / Ваня Максимов” (@ml4value), 5,711 subscribers as measured 7 August 2026. Telegram Register, tgregister.com/channel/ml4value.

Full measurement history, CC BY 4.0. Every reading this register holds for this entry, not just the latest one, as a dated, downloadable record: CSV · JSON. Free to use with attribution to tgregister.com. Each file carries its own generation timestamp, which is the figure to cite for exactly when the data was retrieved.